{"metadata":{"kernelspec":{"name":"python3","display_name":"Python 3","language":"python"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":50160,"databundleVersionId":7921029,"sourceType":"competition"}],"dockerImageVersionId":30698,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false},"colab":{"provenance":[]}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# G14 Notebook\n\nWelcome to the G14's notebook for the Home Credit Kaggle competition. The goal of this competition is to determine how likely a customer is going to default on an issued loan. The main difference between the [first](https://www.kaggle.com/c/home-credit-default-risk) and this competition is that now your submission will be scored with a custom metric that will take into account how well the model performs in future. A decline in performance will be penalized. The goal is to create a model that is stable and performs well in the future.\n\nIn this notebook you will see how to:\n* Load the data\n* Join tables with Polars - a DataFrame library implemented in Rust language, designed to be blazingy fast and memory efficient. \n* Create simple aggregation features\n* Train a LightGBM model\n* Create a submission table\n\n## Load the data","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","id":"UT9kpBithazL"}},{"cell_type":"code","source":"import polars as pl\nimport numpy as np\nimport pandas as pd\nimport lightgbm as lgb\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import roc_auc_score\n\ndataPath = \"/kaggle/input/home-credit-credit-risk-model-stability/\"","metadata":{"id":"Mm_NGuihhazM","execution":{"iopub.status.busy":"2024-04-22T00:44:54.022225Z","iopub.execute_input":"2024-04-22T00:44:54.022627Z","iopub.status.idle":"2024-04-22T00:44:59.928601Z","shell.execute_reply.started":"2024-04-22T00:44:54.022597Z","shell.execute_reply":"2024-04-22T00:44:59.927286Z"},"trusted":true},"execution_count":1,"outputs":[]},{"cell_type":"code","source":"def set_table_dtypes(df: pl.DataFrame) -> pl.DataFrame:\n # implement here all desired dtypes for tables\n # the following is just an example\n for col in df.columns:\n # last letter of column name will help you determine the type\n if col[-1] in (\"P\", \"A\"):\n df = df.with_columns(pl.col(col).cast(pl.Float64).alias(col))\n\n return df\n\ndef convert_strings(df: pd.DataFrame) -> pd.DataFrame:\n for col in df.columns:\n if df[col].dtype.name in ['object', 'string']:\n df[col] = df[col].astype(\"string\").astype('category')\n current_categories = df[col].cat.categories\n new_categories = current_categories.to_list() + [\"Unknown\"]\n new_dtype = pd.CategoricalDtype(categories=new_categories, ordered=True)\n df[col] = df[col].astype(new_dtype)\n return df","metadata":{"id":"So9JN4arhazM","execution":{"iopub.status.busy":"2024-04-22T00:44:59.931032Z","iopub.execute_input":"2024-04-22T00:44:59.932394Z","iopub.status.idle":"2024-04-22T00:44:59.944564Z","shell.execute_reply.started":"2024-04-22T00:44:59.932346Z","shell.execute_reply":"2024-04-22T00:44:59.942742Z"},"trusted":true},"execution_count":2,"outputs":[]},{"cell_type":"code","source":"train_basetable = pl.read_csv(dataPath + \"csv_files/train/train_base.csv\")\ntrain_static = pl.concat(\n [\n pl.read_csv(dataPath + \"csv_files/train/train_static_0_0.csv\").pipe(set_table_dtypes),\n pl.read_csv(dataPath + \"csv_files/train/train_static_0_1.csv\").pipe(set_table_dtypes),\n ],\n how=\"vertical_relaxed\",\n)\ntrain_static_cb = pl.read_csv(dataPath + \"csv_files/train/train_static_cb_0.csv\").pipe(set_table_dtypes)\ntrain_person_1 = pl.read_csv(dataPath + \"csv_files/train/train_person_1.csv\").pipe(set_table_dtypes)\ntrain_credit_bureau_b_2 = pl.read_csv(dataPath + \"csv_files/train/train_credit_bureau_b_2.csv\").pipe(set_table_dtypes)","metadata":{"id":"BokoNCmAhazM","execution":{"iopub.status.busy":"2024-04-22T00:44:59.94643Z","iopub.execute_input":"2024-04-22T00:44:59.946847Z","iopub.status.idle":"2024-04-22T00:45:20.491242Z","shell.execute_reply.started":"2024-04-22T00:44:59.946808Z","shell.execute_reply":"2024-04-22T00:45:20.490264Z"},"trusted":true},"execution_count":3,"outputs":[]},{"cell_type":"code","source":"test_basetable = pl.read_csv(dataPath + \"csv_files/test/test_base.csv\")\ntest_static = pl.concat(\n [\n pl.read_csv(dataPath + \"csv_files/test/test_static_0_0.csv\").pipe(set_table_dtypes),\n pl.read_csv(dataPath + \"csv_files/test/test_static_0_1.csv\").pipe(set_table_dtypes),\n pl.read_csv(dataPath + \"csv_files/test/test_static_0_2.csv\").pipe(set_table_dtypes),\n ],\n how=\"vertical_relaxed\",\n)\ntest_static_cb = pl.read_csv(dataPath + \"csv_files/test/test_static_cb_0.csv\").pipe(set_table_dtypes)\ntest_person_1 = pl.read_csv(dataPath + \"csv_files/test/test_person_1.csv\").pipe(set_table_dtypes)\ntest_credit_bureau_b_2 = pl.read_csv(dataPath + \"csv_files/test/test_credit_bureau_b_2.csv\").pipe(set_table_dtypes)","metadata":{"id":"-W_f8daUhazN","execution":{"iopub.status.busy":"2024-04-22T00:45:20.494592Z","iopub.execute_input":"2024-04-22T00:45:20.495878Z","iopub.status.idle":"2024-04-22T00:45:20.572387Z","shell.execute_reply.started":"2024-04-22T00:45:20.495829Z","shell.execute_reply":"2024-04-22T00:45:20.570741Z"},"trusted":true},"execution_count":4,"outputs":[]},{"cell_type":"markdown","source":"## Feature engineering\n\nIn this part, we can see a simple example of joining tables via `case_id`. Here the loading and joining is done with polars library. Polars library is blazingly fast and has much smaller memory footprint than pandas.","metadata":{"id":"qwO6_7-ZhazN"}},{"cell_type":"code","source":"# We need to use aggregation functions in tables with depth > 1, so tables that contain num_group1 column or\n# also num_group2 column.\ntrain_person_1_feats_1 = train_person_1.group_by(\"case_id\").agg(\n pl.col(\"mainoccupationinc_384A\").max().alias(\"mainoccupationinc_384A_max\"),\n (pl.col(\"incometype_1044T\") == \"SELFEMPLOYED\").max().alias(\"mainoccupationinc_384A_any_selfemployed\")\n)\n\n# Here num_group1=0 has special meaning, it is the person who applied for the loan.\ntrain_person_1_feats_2 = train_person_1.select([\"case_id\", \"num_group1\", \"housetype_905L\"]).filter(\n pl.col(\"num_group1\") == 0\n).drop(\"num_group1\").rename({\"housetype_905L\": \"person_housetype\"})\n\n# Here we have num_goup1 and num_group2, so we need to aggregate again.\ntrain_credit_bureau_b_2_feats = train_credit_bureau_b_2.group_by(\"case_id\").agg(\n pl.col(\"pmts_pmtsoverdue_635A\").max().alias(\"pmts_pmtsoverdue_635A_max\"),\n (pl.col(\"pmts_dpdvalue_108P\") > 31).max().alias(\"pmts_dpdvalue_108P_over31\")\n)\n\n# We will process in this examples only A-type and M-type columns, so we need to select them.\nselected_static_cols = []\nfor col in train_static.columns:\n if col[-1] in (\"A\", \"M\"):\n selected_static_cols.append(col)\nprint(selected_static_cols)\n\nselected_static_cb_cols = []\nfor col in train_static_cb.columns:\n if col[-1] in (\"A\", \"M\"):\n selected_static_cb_cols.append(col)\nprint(selected_static_cb_cols)\n\n# Join all tables together.\ndata = train_basetable.join(\n train_static.select([\"case_id\"]+selected_static_cols), how=\"left\", on=\"case_id\"\n).join(\n train_static_cb.select([\"case_id\"]+selected_static_cb_cols), how=\"left\", on=\"case_id\"\n).join(\n train_person_1_feats_1, how=\"left\", on=\"case_id\"\n).join(\n train_person_1_feats_2, how=\"left\", on=\"case_id\"\n).join(\n train_credit_bureau_b_2_feats, how=\"left\", on=\"case_id\"\n)","metadata":{"id":"GIqz49P_hazN","colab":{"base_uri":"https://localhost:8080/"},"outputId":"e34be669-f60e-444b-91c3-a572e792dedf","execution":{"iopub.status.busy":"2024-04-22T00:45:20.575816Z","iopub.execute_input":"2024-04-22T00:45:20.576718Z","iopub.status.idle":"2024-04-22T00:45:23.64295Z","shell.execute_reply.started":"2024-04-22T00:45:20.576658Z","shell.execute_reply":"2024-04-22T00:45:23.641679Z"},"trusted":true},"execution_count":5,"outputs":[{"name":"stdout","text":"['amtinstpaidbefduel24m_4187115A', 'annuity_780A', 'annuitynextmonth_57A', 'avginstallast24m_3658937A', 'avglnamtstart24m_4525187A', 'avgoutstandbalancel6m_4187114A', 'avgpmtlast12m_4525200A', 'credamount_770A', 'currdebt_22A', 'currdebtcredtyperange_828A', 'disbursedcredamount_1113A', 'downpmt_116A', 'inittransactionamount_650A', 'lastapprcommoditycat_1041M', 'lastapprcommoditytypec_5251766M', 'lastapprcredamount_781A', 'lastcancelreason_561M', 'lastotherinc_902A', 'lastotherlnsexpense_631A', 'lastrejectcommoditycat_161M', 'lastrejectcommodtypec_5251769M', 'lastrejectcredamount_222A', 'lastrejectreason_759M', 'lastrejectreasonclient_4145040M', 'maininc_215A', 'maxannuity_159A', 'maxannuity_4075009A', 'maxdebt4_972A', 'maxinstallast24m_3658928A', 'maxlnamtstart6m_4525199A', 'maxoutstandbalancel12m_4187113A', 'maxpmtlast3m_4525190A', 'previouscontdistrict_112M', 'price_1097A', 'sumoutstandtotal_3546847A', 'sumoutstandtotalest_4493215A', 'totaldebt_9A', 'totalsettled_863A', 'totinstallast1m_4525188A']\n['description_5085714M', 'education_1103M', 'education_88M', 'maritalst_385M', 'maritalst_893M', 'pmtaverage_3A', 'pmtaverage_4527227A', 'pmtaverage_4955615A', 'pmtssum_45A']\n","output_type":"stream"}]},{"cell_type":"code","source":"test_person_1_feats_1 = test_person_1.group_by(\"case_id\").agg(\n pl.col(\"mainoccupationinc_384A\").max().alias(\"mainoccupationinc_384A_max\"),\n (pl.col(\"incometype_1044T\") == \"SELFEMPLOYED\").max().alias(\"mainoccupationinc_384A_any_selfemployed\")\n)\n\ntest_person_1_feats_2 = test_person_1.select([\"case_id\", \"num_group1\", \"housetype_905L\"]).filter(\n pl.col(\"num_group1\") == 0\n).drop(\"num_group1\").rename({\"housetype_905L\": \"person_housetype\"})\n\ntest_credit_bureau_b_2_feats = test_credit_bureau_b_2.group_by(\"case_id\").agg(\n pl.col(\"pmts_pmtsoverdue_635A\").max().alias(\"pmts_pmtsoverdue_635A_max\"),\n (pl.col(\"pmts_dpdvalue_108P\") > 31).max().alias(\"pmts_dpdvalue_108P_over31\")\n)\n\ndata_submission = test_basetable.join(\n test_static.select([\"case_id\"]+selected_static_cols), how=\"left\", on=\"case_id\"\n).join(\n test_static_cb.select([\"case_id\"]+selected_static_cb_cols), how=\"left\", on=\"case_id\"\n).join(\n test_person_1_feats_1, how=\"left\", on=\"case_id\"\n).join(\n test_person_1_feats_2, how=\"left\", on=\"case_id\"\n).join(\n test_credit_bureau_b_2_feats, how=\"left\", on=\"case_id\"\n)","metadata":{"id":"0Dut4oHchazN","execution":{"iopub.status.busy":"2024-04-22T00:45:23.644376Z","iopub.execute_input":"2024-04-22T00:45:23.645641Z","iopub.status.idle":"2024-04-22T00:45:23.66302Z","shell.execute_reply.started":"2024-04-22T00:45:23.645601Z","shell.execute_reply":"2024-04-22T00:45:23.661482Z"},"trusted":true},"execution_count":6,"outputs":[]},{"cell_type":"markdown","source":"# **Feature Analysis**","metadata":{"id":"xadvPZhFhazN"}},{"cell_type":"markdown","source":"# EDA","metadata":{"id":"clv3igyThazN"}},{"cell_type":"code","source":"pd_df = data.to_pandas() # dask, koalas : some alternatives foe EDA\nprint('Polar Dataframe')\nprint(type(pd_df))\nprint('Overall data analytics')\nprint(pd_df.describe())\nprint('Data types')\nprint(pd_df.dtypes)\n","metadata":{"id":"7XW-T4JUhazN","colab":{"base_uri":"https://localhost:8080/"},"outputId":"86016ca0-12f3-492b-ef56-d7fc5d85b3f0","execution":{"iopub.status.busy":"2024-04-22T00:45:23.665414Z","iopub.execute_input":"2024-04-22T00:45:23.666404Z","iopub.status.idle":"2024-04-22T00:45:29.208639Z","shell.execute_reply.started":"2024-04-22T00:45:23.666365Z","shell.execute_reply":"2024-04-22T00:45:29.207602Z"},"trusted":true},"execution_count":7,"outputs":[{"name":"stdout","text":"Polar Dataframe\n\nOverall data analytics\n case_id MONTH WEEK_NUM target \\\ncount 1.526659e+06 1.526659e+06 1.526659e+06 1.526659e+06 \nmean 1.286077e+06 2.019363e+05 4.076904e+01 3.143728e-02 \nstd 7.189466e+05 4.473597e+01 2.379798e+01 1.744964e-01 \nmin 0.000000e+00 2.019010e+05 0.000000e+00 0.000000e+00 \n25% 7.661975e+05 2.019060e+05 2.300000e+01 0.000000e+00 \n50% 1.357358e+06 2.019100e+05 4.000000e+01 0.000000e+00 \n75% 1.739022e+06 2.020010e+05 5.500000e+01 0.000000e+00 \nmax 2.703454e+06 2.020100e+05 9.100000e+01 1.000000e+00 \n\n amtinstpaidbefduel24m_4187115A annuity_780A annuitynextmonth_57A \\\ncount 9.655350e+05 1.526659e+06 1.526655e+06 \nmean 5.595833e+04 4.039207e+03 1.435775e+03 \nstd 7.161417e+04 3.006608e+03 2.807021e+03 \nmin 0.000000e+00 8.080000e+01 0.000000e+00 \n25% 7.419200e+03 1.967600e+03 0.000000e+00 \n50% 2.975840e+04 3.151800e+03 0.000000e+00 \n75% 7.630295e+04 5.231400e+03 2.029400e+03 \nmax 1.408010e+06 1.060070e+05 8.750000e+04 \n\n avginstallast24m_3658937A avglnamtstart24m_4525187A \\\ncount 901784.000000 162509.000000 \nmean 5401.587636 44717.566753 \nstd 6531.562344 44844.786730 \nmin 0.000000 0.000000 \n25% 2528.400100 15682.601000 \n50% 4068.600000 28419.400000 \n75% 6551.800300 56334.200000 \nmax 496148.800000 513520.000000 \n\n avgoutstandbalancel6m_4187114A ... sumoutstandtotalest_4493215A \\\ncount 6.854780e+05 ... 6.860130e+05 \nmean 4.598483e+04 ... 2.830974e+04 \nstd 6.399392e+04 ... 6.050010e+04 \nmin -7.588198e+06 ... -2.504400e+04 \n25% 8.708660e+03 ... 0.000000e+00 \n50% 2.275459e+04 ... 0.000000e+00 \n75% 5.542953e+04 ... 2.798400e+04 \nmax 1.131136e+06 ... 1.085048e+06 \n\n totaldebt_9A totalsettled_863A totinstallast1m_4525188A \\\ncount 1.526656e+06 1.526655e+06 352448.000000 \nmean 1.968312e+04 9.223817e+04 10411.377565 \nstd 5.083603e+04 1.623358e+05 16222.912082 \nmin 0.000000e+00 0.000000e+00 0.214000 \n25% 0.000000e+00 0.000000e+00 3309.314000 \n50% 0.000000e+00 3.597766e+04 6221.200000 \n75% 1.349310e+04 1.188157e+05 11685.000000 \nmax 1.210629e+06 4.803504e+07 794899.200000 \n\n pmtaverage_3A pmtaverage_4527227A pmtaverage_4955615A pmtssum_45A \\\ncount 143589.000000 114978.000000 71845.000000 572638.000000 \nmean 9303.171700 10033.556094 17651.732489 13199.935970 \nstd 5562.386995 5455.843604 6871.642301 18117.218312 \nmin 0.000000 4.200000 4.400000 0.000000 \n25% 6590.600000 7192.000000 13664.601000 3156.400100 \n50% 7305.900000 7553.000000 15765.200000 8391.900000 \n75% 13023.900000 13464.400000 21840.000000 16992.000000 \nmax 145257.400000 205848.610000 99085.400000 476843.400000 \n\n mainoccupationinc_384A_max pmts_pmtsoverdue_635A_max \ncount 1.526659e+06 36415.000000 \nmean 5.770748e+04 36.426704 \nstd 3.334830e+04 1547.789956 \nmin 0.000000e+00 0.000000 \n25% 3.600000e+04 0.000000 \n50% 5.000000e+04 0.000000 \n75% 7.000000e+04 2.600000 \nmax 2.000000e+05 147470.610000 \n\n[8 rows x 41 columns]\nData types\ncase_id int64\ndate_decision object\nMONTH int64\nWEEK_NUM int64\ntarget int64\namtinstpaidbefduel24m_4187115A float64\nannuity_780A float64\nannuitynextmonth_57A float64\navginstallast24m_3658937A float64\navglnamtstart24m_4525187A float64\navgoutstandbalancel6m_4187114A float64\navgpmtlast12m_4525200A float64\ncredamount_770A float64\ncurrdebt_22A float64\ncurrdebtcredtyperange_828A float64\ndisbursedcredamount_1113A float64\ndownpmt_116A float64\ninittransactionamount_650A float64\nlastapprcommoditycat_1041M object\nlastapprcommoditytypec_5251766M object\nlastapprcredamount_781A float64\nlastcancelreason_561M object\nlastotherinc_902A float64\nlastotherlnsexpense_631A float64\nlastrejectcommoditycat_161M object\nlastrejectcommodtypec_5251769M object\nlastrejectcredamount_222A float64\nlastrejectreason_759M object\nlastrejectreasonclient_4145040M object\nmaininc_215A float64\nmaxannuity_159A float64\nmaxannuity_4075009A float64\nmaxdebt4_972A float64\nmaxinstallast24m_3658928A float64\nmaxlnamtstart6m_4525199A float64\nmaxoutstandbalancel12m_4187113A float64\nmaxpmtlast3m_4525190A float64\npreviouscontdistrict_112M object\nprice_1097A float64\nsumoutstandtotal_3546847A float64\nsumoutstandtotalest_4493215A float64\ntotaldebt_9A float64\ntotalsettled_863A float64\ntotinstallast1m_4525188A float64\ndescription_5085714M object\neducation_1103M object\neducation_88M object\nmaritalst_385M object\nmaritalst_893M object\npmtaverage_3A float64\npmtaverage_4527227A float64\npmtaverage_4955615A float64\npmtssum_45A float64\nmainoccupationinc_384A_max float64\nmainoccupationinc_384A_any_selfemployed bool\nperson_housetype object\npmts_pmtsoverdue_635A_max float64\npmts_dpdvalue_108P_over31 object\ndtype: object\n","output_type":"stream"}]},{"cell_type":"markdown","source":"# Correlation Analysis\n\ncorrelation matrix performed on Int and Float values within dataset. No features have a strong relationship with the target feature.","metadata":{"id":"g60hL44jhazO"}},{"cell_type":"code","source":"\n\n#Correlation Analysis\nimport seaborn as sns\nimport matplotlib.pyplot as plt\n\nnumerical_columns = pd_df.select_dtypes(include=['float64', 'int64']).columns\n\n# Subset DataFrame with numerical columns\nnumerical_df = pd_df[numerical_columns]\n\n# Example 1: Correlation Analysis\ncorrelation_matrix = numerical_df.corr()\n\n# Set up the matplotlib figure\nplt.figure(figsize=(12, 10))\n\n# Draw the heatmap\nsns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', fmt=\".2f\")\n\n# Rotate column labels\nplt.xticks(rotation=45) # Rotate x-axis labels by 45 degrees\n\n# Set the title\nplt.title('Correlation Matrix of Numerical Columns')\n\n# Show the plot\nplt.show()\n\nthreshold = 0.8 # Adjust as needed\n\n# Extract pairs of columns with high correlation\nhigh_correlation_pairs = []\n\n# Loop through the correlation matrix\nfor i in range(len(correlation_matrix.columns)):\n for j in range(i+1, len(correlation_matrix.columns)):\n if abs(correlation_matrix.iloc[i, j]) >= threshold:\n pair = (correlation_matrix.columns[i], correlation_matrix.columns[j], correlation_matrix.iloc[i, j])\n high_correlation_pairs.append(pair)\n\n# Print high correlation pairs\nprint(\"Pairs with correlation coefficient >= \", threshold)\nfor pair in high_correlation_pairs:\n print(pair)\n\ntarget_correlation = correlation_matrix['target'].drop('target') # Drop target variable itself\ntarget_correlation_with_target = target_correlation.abs().sort_values(ascending=False)\nprint(\"\\nCorrelation with Target:\")\nprint(target_correlation_with_target)","metadata":{"id":"U5J-p5CzhazO","colab":{"base_uri":"https://localhost:8080/","height":1000},"outputId":"d6997d83-8ed6-4c7b-c47f-eb6ebde04f6b","execution":{"iopub.status.busy":"2024-04-22T00:45:29.210532Z","iopub.execute_input":"2024-04-22T00:45:29.210963Z","iopub.status.idle":"2024-04-22T00:45:40.600503Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#### Drop the highly correlated columns from each pair, which aren't related to the target value","metadata":{"id":"e6vDYX1ghazO"}},{"cell_type":"code","source":"# Pairs with correlation coefficient >= 0.8\ncorrelated_pairs = [\n #('MONTH', 'WEEK_NUM'),\n ('amtinstpaidbefduel24m_4187115A', 'maxdebt4_972A'),\n ('annuity_780A', 'credamount_770A'),\n ('avginstallast24m_3658937A', 'avgpmtlast12m_4525200A'),\n ('avgoutstandbalancel6m_4187114A', 'currdebt_22A'),\n ('avgoutstandbalancel6m_4187114A', 'maxoutstandbalancel12m_4187113A'),\n ('avgoutstandbalancel6m_4187114A', 'sumoutstandtotal_3546847A'),\n ('avgoutstandbalancel6m_4187114A', 'sumoutstandtotalest_4493215A'),\n ('avgoutstandbalancel6m_4187114A', 'totaldebt_9A'),\n ('credamount_770A', 'disbursedcredamount_1113A'),\n ('currdebt_22A', 'maxoutstandbalancel12m_4187113A'),\n ('currdebt_22A', 'sumoutstandtotal_3546847A'),\n ('currdebt_22A', 'sumoutstandtotalest_4493215A'),\n ('currdebt_22A', 'totaldebt_9A'),\n ('disbursedcredamount_1113A', 'inittransactionamount_650A'),\n ('inittransactionamount_650A', 'price_1097A'),\n ('maxoutstandbalancel12m_4187113A', 'sumoutstandtotal_3546847A'),\n ('maxoutstandbalancel12m_4187113A', 'sumoutstandtotalest_4493215A'),\n ('maxoutstandbalancel12m_4187113A', 'totaldebt_9A'),\n ('maxpmtlast3m_4525190A', 'totinstallast1m_4525188A'),\n ('sumoutstandtotal_3546847A', 'sumoutstandtotalest_4493215A'),\n ('sumoutstandtotal_3546847A', 'totaldebt_9A'),\n ('sumoutstandtotalest_4493215A', 'totaldebt_9A'),\n ('pmtaverage_3A', 'pmtaverage_4527227A'),\n ('pmtaverage_4527227A', 'pmtaverage_4955615A')\n]\n\n# Correlation of each column with the target variable\ncorrelation_with_target = {\n 'pmtaverage_4527227A': 0.056869,\n 'pmtaverage_3A': 0.052846,\n 'pmtssum_45A': 0.045376,\n 'amtinstpaidbefduel24m_4187115A': 0.045047,\n 'pmtaverage_4955615A': 0.043715,\n 'avglnamtstart24m_4525187A': 0.029916,\n 'disbursedcredamount_1113A': 0.027877,\n 'sumoutstandtotalest_4493215A': 0.027050,\n 'price_1097A': 0.026889,\n 'credamount_770A': 0.026277,\n 'maxdebt4_972A': 0.025744,\n 'sumoutstandtotal_3546847A': 0.021917,\n 'totaldebt_9A': 0.021764,\n 'currdebt_22A': 0.021745,\n 'totalsettled_863A': 0.019596,\n 'avgoutstandbalancel6m_4187114A': 0.017543,\n 'currdebtcredtyperange_828A': 0.017442,\n 'annuity_780A': 0.013838,\n 'maxannuity_159A': 0.013249,\n 'inittransactionamount_650A': 0.013203,\n 'pmts_pmtsoverdue_635A_max': 0.012941,\n 'lastotherlnsexpense_631A': 0.012272,\n 'maininc_215A': 0.011394,\n 'lastrejectcredamount_222A': 0.011019,\n 'lastotherinc_902A': 0.010642,\n 'maxannuity_4075009A': 0.010332,\n 'lastapprcredamount_781A': 0.008283,\n 'maxoutstandbalancel12m_4187113A': 0.006408,\n 'annuitynextmonth_57A': 0.006378,\n 'mainoccupationinc_384A_max': 0.006057,\n 'avginstallast24m_3658937A': 0.005615,\n 'downpmt_116A': 0.005212,\n 'MONTH': 0.004875,\n 'case_id': 0.003834,\n 'maxlnamtstart6m_4525199A': 0.003773,\n #'WEEK_NUM': 0.002969,\n 'totinstallast1m_4525188A': 0.002263,\n 'avgpmtlast12m_4525200A': 0.001701,\n 'maxinstallast24m_3658928A': 0.001042,\n 'maxpmtlast3m_4525190A': 0.000932\n}\n\n# Dictionary to store the selected column from each pair\nselected_columns = {}\n\n# Iterate through correlated pairs\nfor pair in correlated_pairs:\n column1, column2 = pair\n # Choose the column with the lower absolute correlation with the target\n if abs(correlation_with_target[column1]) < abs(correlation_with_target[column2]):\n selected_columns[pair] = column1\n else:\n selected_columns[pair] = column2\n\n# Print the selected columns\nfor pair, column in selected_columns.items():\n# print(f\"Column from pair {pair} with lower correlation to target: {column}\")\n print(column)\n","metadata":{"id":"ezx0TIzKhazO","colab":{"base_uri":"https://localhost:8080/"},"outputId":"2a51bfd7-125d-4c41-8d55-448fe707c4b8","execution":{"iopub.status.busy":"2024-04-22T00:45:40.60219Z","iopub.execute_input":"2024-04-22T00:45:40.602576Z","iopub.status.idle":"2024-04-22T00:45:40.623168Z"},"trusted":true},"execution_count":null,"outputs":[{"name":"stdout","text":"maxdebt4_972A\nannuity_780A\navgpmtlast12m_4525200A\navgoutstandbalancel6m_4187114A\nmaxoutstandbalancel12m_4187113A\navgoutstandbalancel6m_4187114A\navgoutstandbalancel6m_4187114A\navgoutstandbalancel6m_4187114A\ncredamount_770A\nmaxoutstandbalancel12m_4187113A\ncurrdebt_22A\ncurrdebt_22A\ncurrdebt_22A\ninittransactionamount_650A\ninittransactionamount_650A\nmaxoutstandbalancel12m_4187113A\nmaxoutstandbalancel12m_4187113A\nmaxoutstandbalancel12m_4187113A\nmaxpmtlast3m_4525190A\nsumoutstandtotal_3546847A\ntotaldebt_9A\ntotaldebt_9A\npmtaverage_3A\npmtaverage_4955615A\n","output_type":"stream"}]},{"cell_type":"code","source":"columns_to_drop = []\n\nfor pair, column in selected_columns.items():\n columns_to_drop.append(column)\n\n# Drop columns from the main DataFrame\npd_df.drop(columns=columns_to_drop, inplace=True)\npd_df","metadata":{"id":"e0FDG6A6hazO","colab":{"base_uri":"https://localhost:8080/","height":439},"outputId":"4f9b7755-7c0c-46af-fdb4-e16c75a20fee","execution":{"iopub.status.busy":"2024-04-22T00:45:40.628211Z","iopub.execute_input":"2024-04-22T00:45:40.628648Z","iopub.status.idle":"2024-04-22T00:45:42.338853Z","shell.execute_reply.started":"2024-04-22T00:45:40.628564Z","shell.execute_reply":"2024-04-22T00:45:42.336869Z"},"trusted":true},"execution_count":10,"outputs":[{"execution_count":10,"output_type":"execute_result","data":{"text/plain":" case_id date_decision MONTH WEEK_NUM target \\\n0 0 2019-01-03 201901 0 0 \n1 1 2019-01-03 201901 0 0 \n2 2 2019-01-04 201901 0 0 \n3 3 2019-01-03 201901 0 0 \n4 4 2019-01-04 201901 0 1 \n... ... ... ... ... ... \n1526654 2703450 2020-10-05 202010 91 0 \n1526655 2703451 2020-10-05 202010 91 0 \n1526656 2703452 2020-10-05 202010 91 0 \n1526657 2703453 2020-10-05 202010 91 0 \n1526658 2703454 2020-10-05 202010 91 0 \n\n amtinstpaidbefduel24m_4187115A annuitynextmonth_57A \\\n0 NaN 0.0 \n1 NaN 0.0 \n2 NaN 0.0 \n3 NaN 0.0 \n4 NaN 0.0 \n... ... ... \n1526654 176561.36 0.0 \n1526655 301276.47 6191.6 \n1526656 14232.40 0.0 \n1526657 197371.58 2827.2 \n1526658 82949.60 2986.8 \n\n avginstallast24m_3658937A avglnamtstart24m_4525187A \\\n0 NaN NaN \n1 NaN NaN \n2 NaN NaN \n3 NaN NaN \n4 NaN NaN \n... ... ... \n1526654 7356.8003 NaN \n1526655 12553.2000 NaN \n1526656 2662.4001 NaN \n1526657 8212.6010 NaN \n1526658 6405.4000 15998.0 \n\n currdebtcredtyperange_828A ... education_88M maritalst_385M \\\n0 0.0 ... None None \n1 0.0 ... None None \n2 0.0 ... None None \n3 0.0 ... None None \n4 0.0 ... None None \n... ... ... ... ... \n1526654 0.0 ... a55475b1 a55475b1 \n1526655 68098.4 ... a55475b1 a55475b1 \n1526656 0.0 ... a55475b1 a55475b1 \n1526657 46806.6 ... a55475b1 3439d993 \n1526658 0.0 ... a55475b1 b6cabe76 \n\n maritalst_893M pmtaverage_4527227A pmtssum_45A \\\n0 None NaN NaN \n1 None NaN NaN \n2 None NaN NaN \n3 None NaN NaN \n4 None NaN NaN \n... ... ... ... \n1526654 a55475b1 NaN NaN \n1526655 a55475b1 NaN NaN \n1526656 a55475b1 NaN NaN \n1526657 a55475b1 NaN NaN \n1526658 a55475b1 NaN NaN \n\n mainoccupationinc_384A_max mainoccupationinc_384A_any_selfemployed \\\n0 10800.0 False \n1 10000.0 False \n2 14000.0 False \n3 10000.0 False \n4 24000.0 False \n... ... ... \n1526654 40000.0 False \n1526655 36800.0 False \n1526656 30000.0 False \n1526657 30000.0 False \n1526658 39400.0 False \n\n person_housetype pmts_pmtsoverdue_635A_max pmts_dpdvalue_108P_over31 \n0 None NaN None \n1 None NaN None \n2 None NaN None \n3 None NaN None \n4 None NaN None \n... ... ... ... \n1526654 OWNED NaN None \n1526655 None NaN None \n1526656 None NaN None \n1526657 None NaN None \n1526658 None NaN None \n\n[1526659 rows x 45 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
case_iddate_decisionMONTHWEEK_NUMtargetamtinstpaidbefduel24m_4187115Aannuitynextmonth_57Aavginstallast24m_3658937Aavglnamtstart24m_4525187Acurrdebtcredtyperange_828A...education_88Mmaritalst_385Mmaritalst_893Mpmtaverage_4527227Apmtssum_45Amainoccupationinc_384A_maxmainoccupationinc_384A_any_selfemployedperson_housetypepmts_pmtsoverdue_635A_maxpmts_dpdvalue_108P_over31
002019-01-0320190100NaN0.0NaNNaN0.0...NoneNoneNoneNaNNaN10800.0FalseNoneNaNNone
112019-01-0320190100NaN0.0NaNNaN0.0...NoneNoneNoneNaNNaN10000.0FalseNoneNaNNone
222019-01-0420190100NaN0.0NaNNaN0.0...NoneNoneNoneNaNNaN14000.0FalseNoneNaNNone
332019-01-0320190100NaN0.0NaNNaN0.0...NoneNoneNoneNaNNaN10000.0FalseNoneNaNNone
442019-01-0420190101NaN0.0NaNNaN0.0...NoneNoneNoneNaNNaN24000.0FalseNoneNaNNone
..................................................................
152665427034502020-10-05202010910176561.360.07356.8003NaN0.0...a55475b1a55475b1a55475b1NaNNaN40000.0FalseOWNEDNaNNone
152665527034512020-10-05202010910301276.476191.612553.2000NaN68098.4...a55475b1a55475b1a55475b1NaNNaN36800.0FalseNoneNaNNone
152665627034522020-10-0520201091014232.400.02662.4001NaN0.0...a55475b1a55475b1a55475b1NaNNaN30000.0FalseNoneNaNNone
152665727034532020-10-05202010910197371.582827.28212.6010NaN46806.6...a55475b13439d993a55475b1NaNNaN30000.0FalseNoneNaNNone
152665827034542020-10-0520201091082949.602986.86405.400015998.00.0...a55475b1b6cabe76a55475b1NaNNaN39400.0FalseNoneNaNNone
\n

1526659 rows × 45 columns

\n
"},"metadata":{}}]},{"cell_type":"markdown","source":"drop the less correlated columns","metadata":{"id":"_n83ddlEhazO"}},{"cell_type":"markdown","source":"# Handling Nan Vaues","metadata":{"id":"XHDUzxQrhazP"}},{"cell_type":"code","source":"pd_df.isnull().sum()","metadata":{"id":"xePbLjeqhazP","colab":{"base_uri":"https://localhost:8080/"},"outputId":"c80cc22e-1e68-404c-8162-cda53b39bc9f","execution":{"iopub.status.busy":"2024-04-22T00:45:42.340951Z","iopub.execute_input":"2024-04-22T00:45:42.341383Z","iopub.status.idle":"2024-04-22T00:45:44.749394Z","shell.execute_reply.started":"2024-04-22T00:45:42.341353Z","shell.execute_reply":"2024-04-22T00:45:44.748337Z"},"trusted":true},"execution_count":11,"outputs":[{"execution_count":11,"output_type":"execute_result","data":{"text/plain":"case_id 0\ndate_decision 0\nMONTH 0\nWEEK_NUM 0\ntarget 0\namtinstpaidbefduel24m_4187115A 561124\nannuitynextmonth_57A 4\navginstallast24m_3658937A 624875\navglnamtstart24m_4525187A 1364150\ncurrdebtcredtyperange_828A 4\ndisbursedcredamount_1113A 0\ndownpmt_116A 0\nlastapprcommoditycat_1041M 0\nlastapprcommoditytypec_5251766M 0\nlastapprcredamount_781A 442041\nlastcancelreason_561M 0\nlastotherinc_902A 1523603\nlastotherlnsexpense_631A 1523601\nlastrejectcommoditycat_161M 0\nlastrejectcommodtypec_5251769M 0\nlastrejectcredamount_222A 769046\nlastrejectreason_759M 0\nlastrejectreasonclient_4145040M 0\nmaininc_215A 511255\nmaxannuity_159A 306019\nmaxannuity_4075009A 1450726\nmaxinstallast24m_3658928A 624875\nmaxlnamtstart6m_4525199A 1032856\npreviouscontdistrict_112M 0\nprice_1097A 223240\nsumoutstandtotalest_4493215A 840646\ntotalsettled_863A 4\ntotinstallast1m_4525188A 1174211\ndescription_5085714M 26183\neducation_1103M 26183\neducation_88M 26183\nmaritalst_385M 26183\nmaritalst_893M 26183\npmtaverage_4527227A 1411681\npmtssum_45A 954021\nmainoccupationinc_384A_max 0\nmainoccupationinc_384A_any_selfemployed 0\nperson_housetype 1425841\npmts_pmtsoverdue_635A_max 1490244\npmts_dpdvalue_108P_over31 1490244\ndtype: int64"},"metadata":{}}]},{"cell_type":"code","source":"null_counts = pd_df.isnull().sum()\ncolumns_to_drop = null_counts[null_counts < 5].index\n\n# Drop rows where any of the specified columns have null values\npd_df_filtered = pd_df.dropna(subset=columns_to_drop)","metadata":{"id":"ee5OYtw4hazP","execution":{"iopub.status.busy":"2024-04-22T00:45:44.75112Z","iopub.execute_input":"2024-04-22T00:45:44.751904Z","iopub.status.idle":"2024-04-22T00:45:49.56323Z","shell.execute_reply.started":"2024-04-22T00:45:44.751852Z","shell.execute_reply":"2024-04-22T00:45:49.561662Z"},"trusted":true},"execution_count":12,"outputs":[]},{"cell_type":"code","source":"null_counts = pd_df_filtered.isnull().sum()\ncolumns_with_null_values = null_counts[null_counts > 0].index","metadata":{"id":"-n3A66sihazP","execution":{"iopub.status.busy":"2024-04-22T00:45:49.565335Z","iopub.execute_input":"2024-04-22T00:45:49.565945Z","iopub.status.idle":"2024-04-22T00:45:52.017785Z","shell.execute_reply.started":"2024-04-22T00:45:49.565877Z","shell.execute_reply":"2024-04-22T00:45:52.016671Z"},"trusted":true},"execution_count":13,"outputs":[]},{"cell_type":"code","source":"# Iterate through columns with null values\nfor column in columns_with_null_values:\n print(\"Column:\", column)\n print(pd_df_filtered[column].value_counts())\n print()","metadata":{"id":"ZomDTQ2-hazP","colab":{"base_uri":"https://localhost:8080/"},"outputId":"bc72589e-4b47-4f1e-87ca-6e160b0ba815","execution":{"iopub.status.busy":"2024-04-22T00:45:52.019184Z","iopub.execute_input":"2024-04-22T00:45:52.020845Z","iopub.status.idle":"2024-04-22T00:45:54.446956Z","shell.execute_reply.started":"2024-04-22T00:45:52.020795Z","shell.execute_reply":"2024-04-22T00:45:54.445781Z"},"trusted":true},"execution_count":14,"outputs":[{"name":"stdout","text":"Column: amtinstpaidbefduel24m_4187115A\namtinstpaidbefduel24m_4187115A\n0.00 161063\n800.00 89\n6000.00 84\n4000.00 79\n13998.00 76\n ... \n154158.00 1\n31457.40 1\n197189.20 1\n84353.69 1\n82949.60 1\nName: count, Length: 610152, dtype: int64\n\nColumn: avginstallast24m_3658937A\navginstallast24m_3658937A\n800.00000 217\n2000.00000 206\n600.00000 194\n1999.80000 161\n667.20000 150\n ... \n97268.00000 1\n25699.60000 1\n22737.80000 1\n570.60004 1\n17366.40000 1\nName: count, Length: 92853, dtype: int64\n\nColumn: avglnamtstart24m_4525187A\navglnamtstart24m_4525187A\n100000.0 2182\n40000.0 1037\n20000.0 1034\n60000.0 920\n150000.0 866\n ... \n29839.6 1\n45003.2 1\n18600.4 1\n6490.6 1\n18680.6 1\nName: count, Length: 57039, dtype: int64\n\nColumn: lastapprcredamount_781A\nlastapprcredamount_781A\n0.0000 57679\n100000.0000 37549\n20000.0000 23968\n40000.0000 23577\n60000.0000 20633\n ... \n57450.0000 1\n6488.8003 1\n81888.0000 1\n19499.8000 1\n166065.8000 1\nName: count, Length: 129485, dtype: int64\n\nColumn: lastotherinc_902A\nlastotherinc_902A\n0.2000 2353\n0.0000 453\n3000.0000 25\n6000.0000 21\n30000.0000 17\n ... \n6437.2000 1\n4928.8003 1\n13200.0000 1\n10507.2000 1\n8303.2000 1\nName: count, Length: 101, dtype: int64\n\nColumn: lastotherlnsexpense_631A\nlastotherlnsexpense_631A\n0.0 1859\n30000.0 68\n200.0 67\n20000.0 62\n400.0 48\n ... \n39600.0 1\n96000.0 1\n2800.0 1\n2860.0 1\n880.0 1\nName: count, Length: 232, dtype: int64\n\nColumn: lastrejectcredamount_222A\nlastrejectcredamount_222A\n100000.000 56728\n60000.000 43182\n0.000 41303\n40000.000 40769\n20000.000 37582\n ... \n8347.000 1\n18191.201 1\n111768.400 1\n20040.800 1\n93969.200 1\nName: count, Length: 76040, dtype: int64\n\nColumn: maininc_215A\nmaininc_215A\n40000.0 94979\n30000.0 84774\n50000.0 83968\n60000.0 70515\n70000.0 44879\n ... \n51284.2 1\n62052.8 1\n1351.6 1\n29093.0 1\n9088.2 1\nName: count, Length: 7738, dtype: int64\n\nColumn: maxannuity_159A\nmaxannuity_159A\n0.000 149016\n4000.000 10864\n2000.000 8423\n6000.000 8158\n3000.000 7533\n ... \n8273.257 1\n9913.544 1\n34719.070 1\n13521.200 1\n16148.929 1\nName: count, Length: 351075, dtype: int64\n\nColumn: maxannuity_4075009A\nmaxannuity_4075009A\n150000.0 2084\n200000.0 1270\n16060.0 1068\n14440.0 985\n400000.0 834\n ... \n66040.0 1\n78460.0 1\n85380.0 1\n76980.0 1\n60900.0 1\nName: count, Length: 4621, dtype: int64\n\nColumn: maxinstallast24m_3658928A\nmaxinstallast24m_3658928A\n800.000 1772\n600.000 675\n1000.000 427\n2000.000 310\n3000.000 187\n ... \n14031.601 1\n26868.201 1\n25556.201 1\n132006.000 1\n40499.800 1\nName: count, Length: 205591, dtype: int64\n\nColumn: maxlnamtstart6m_4525199A\nmaxlnamtstart6m_4525199A\n100000.000 3885\n0.000 2425\n40000.000 1382\n150000.000 1320\n60000.000 1296\n ... \n47806.600 1\n33874.800 1\n13351.000 1\n52527.402 1\n55411.800 1\nName: count, Length: 229584, dtype: int64\n\nColumn: price_1097A\nprice_1097A\n0.000 164190\n17998.000 6426\n23998.000 5496\n19998.000 5292\n13998.000 5175\n ... \n85782.000 1\n55444.000 1\n15375.601 1\n271912.000 1\n79358.000 1\nName: count, Length: 173566, dtype: int64\n\nColumn: sumoutstandtotalest_4493215A\nsumoutstandtotalest_4493215A\n0.00000 364587\n10.00000 148\n11998.00000 124\n9998.00000 118\n7998.00000 108\n ... \n6534.27830 1\n264839.60000 1\n14874.71300 1\n338.80002 1\n8919.20000 1\nName: count, Length: 252286, dtype: int64\n\nColumn: totinstallast1m_4525188A\ntotinstallast1m_4525188A\n600.000 775\n1200.000 461\n2000.000 219\n3000.000 169\n4000.000 158\n ... \n72853.555 1\n26113.256 1\n16944.357 1\n13971.950 1\n40499.805 1\nName: count, Length: 130315, dtype: int64\n\nColumn: description_5085714M\ndescription_5085714M\na55475b1 1316123\n2fc785b2 184349\nName: count, dtype: int64\n\nColumn: education_1103M\neducation_1103M\na55475b1 859958\n6b2ae0fa 452449\n717ddd49 135342\n39a0853f 47140\nc8e1a1d0 5583\nName: count, dtype: int64\n\nColumn: education_88M\neducation_88M\na55475b1 1484956\n6b2ae0fa 11673\n717ddd49 3280\na34a13c8 437\nc8e1a1d0 126\nName: count, dtype: int64\n\nColumn: maritalst_385M\nmaritalst_385M\na55475b1 661588\n3439d993 550336\na7fcb6e5 201050\nb6cabe76 55900\n38c061ee 26851\necd83604 4747\nName: count, dtype: int64\n\nColumn: maritalst_893M\nmaritalst_893M\na55475b1 1479299\n46b968c3 13889\n1a19667c 5321\n977b2a70 1196\ne18430ff 678\necd83604 89\nName: count, dtype: int64\n\nColumn: pmtaverage_4527227A\npmtaverage_4527227A\n7222.2 6173\n7512.0 5844\n7223.4 3927\n7553.0 3395\n7222.6 2341\n ... \n4947.6 1\n14228.8 1\n9779.8 1\n31933.8 1\n4329.0 1\nName: count, Length: 30526, dtype: int64\n\nColumn: pmtssum_45A\npmtssum_45A\n0.0000 90374\n5100.0000 7001\n6000.0000 3235\n2550.0000 2525\n850.0000 1747\n ... \n7736.0923 1\n18628.9730 1\n21144.0000 1\n22248.3800 1\n23062.0000 1\nName: count, Length: 265229, dtype: int64\n\nColumn: person_housetype\nperson_housetype\nOWNED 94076\nPARENTAL 4212\nFLAT 1501\nCOMPANY_FLAT 641\nCOOP_FLAT 222\nSTATE_FLAT 166\nName: count, dtype: int64\n\nColumn: pmts_pmtsoverdue_635A_max\npmts_pmtsoverdue_635A_max\n0.00000 20304\n0.20000 2247\n0.40000 785\n0.60000 639\n0.80000 638\n ... \n268.80002 1\n366.20000 1\n724.00000 1\n207.80000 1\n628.40000 1\nName: count, Length: 1725, dtype: int64\n\nColumn: pmts_dpdvalue_108P_over31\npmts_dpdvalue_108P_over31\nFalse 20603\nTrue 15812\nName: count, dtype: int64\n\n","output_type":"stream"}]},{"cell_type":"markdown","source":"Need to impute some columns","metadata":{}},{"cell_type":"code","source":"# Array containing column names where avg won't be a good fit for imputation\nspecified_columns = [\n 'amtinstpaidbefduel24m_4187115A', 'lastotherinc_902A', 'lastotherlnsexpense_631A',\n 'maxoutstandbalancel12m_4187113A', 'sumoutstandtotal_3546847A', 'sumoutstandtotalest_4493215A',\n 'description_5085714M', 'education_1103M', 'education_88M', 'maritalst_893M',\n 'pmtssum_45A', 'person_housetype', 'pmts_pmtsoverdue_635A_max'\n]\n\n# Select only numeric columns, excluding specified columns\nnumeric_columns = pd_df_filtered.select_dtypes(include=[np.number]).columns\n# columns_for_mean_imputation = [col for col in numeric_columns if col not in specified_columns and col in columns_with_null_values]\ncolumns_for_mean_imputation = [col for col in numeric_columns if col in columns_with_null_values]\n# FOR NOW, REMOVED THE col not in specified_columns and (I.E. doing mean imputation for all numerical columns containing NaN values)\n\n# Calculate means excluding specified columns\nmeans = pd_df_filtered[columns_for_mean_imputation].mean()\n\n# Replace NaN values with the mean for each eligible column\nfor column in columns_for_mean_imputation:\n pd_df_filtered.loc[pd_df_filtered[column].isna(), column] = means[column]\n\n\nprint(pd_df_filtered)","metadata":{"execution":{"iopub.status.busy":"2024-04-22T00:45:54.448344Z","iopub.execute_input":"2024-04-22T00:45:54.448695Z","iopub.status.idle":"2024-04-22T00:45:55.813115Z","shell.execute_reply.started":"2024-04-22T00:45:54.448665Z","shell.execute_reply":"2024-04-22T00:45:55.812092Z"},"trusted":true},"execution_count":15,"outputs":[{"name":"stdout","text":" case_id date_decision MONTH WEEK_NUM target \\\n0 0 2019-01-03 201901 0 0 \n1 1 2019-01-03 201901 0 0 \n2 2 2019-01-04 201901 0 0 \n3 3 2019-01-03 201901 0 0 \n4 4 2019-01-04 201901 0 1 \n... ... ... ... ... ... \n1526654 2703450 2020-10-05 202010 91 0 \n1526655 2703451 2020-10-05 202010 91 0 \n1526656 2703452 2020-10-05 202010 91 0 \n1526657 2703453 2020-10-05 202010 91 0 \n1526658 2703454 2020-10-05 202010 91 0 \n\n amtinstpaidbefduel24m_4187115A annuitynextmonth_57A \\\n0 55958.371939 0.0 \n1 55958.371939 0.0 \n2 55958.371939 0.0 \n3 55958.371939 0.0 \n4 55958.371939 0.0 \n... ... ... \n1526654 176561.360000 0.0 \n1526655 301276.470000 6191.6 \n1526656 14232.400000 0.0 \n1526657 197371.580000 2827.2 \n1526658 82949.600000 2986.8 \n\n avginstallast24m_3658937A avglnamtstart24m_4525187A \\\n0 5401.590717 44717.566753 \n1 5401.590717 44717.566753 \n2 5401.590717 44717.566753 \n3 5401.590717 44717.566753 \n4 5401.590717 44717.566753 \n... ... ... \n1526654 7356.800300 44717.566753 \n1526655 12553.200000 44717.566753 \n1526656 2662.400100 44717.566753 \n1526657 8212.601000 44717.566753 \n1526658 6405.400000 15998.000000 \n\n currdebtcredtyperange_828A ... education_88M maritalst_385M \\\n0 0.0 ... None None \n1 0.0 ... None None \n2 0.0 ... None None \n3 0.0 ... None None \n4 0.0 ... None None \n... ... ... ... ... \n1526654 0.0 ... a55475b1 a55475b1 \n1526655 68098.4 ... a55475b1 a55475b1 \n1526656 0.0 ... a55475b1 a55475b1 \n1526657 46806.6 ... a55475b1 3439d993 \n1526658 0.0 ... a55475b1 b6cabe76 \n\n maritalst_893M pmtaverage_4527227A pmtssum_45A \\\n0 None 10033.556094 13199.93597 \n1 None 10033.556094 13199.93597 \n2 None 10033.556094 13199.93597 \n3 None 10033.556094 13199.93597 \n4 None 10033.556094 13199.93597 \n... ... ... ... \n1526654 a55475b1 10033.556094 13199.93597 \n1526655 a55475b1 10033.556094 13199.93597 \n1526656 a55475b1 10033.556094 13199.93597 \n1526657 a55475b1 10033.556094 13199.93597 \n1526658 a55475b1 10033.556094 13199.93597 \n\n mainoccupationinc_384A_max mainoccupationinc_384A_any_selfemployed \\\n0 10800.0 False \n1 10000.0 False \n2 14000.0 False \n3 10000.0 False \n4 24000.0 False \n... ... ... \n1526654 40000.0 False \n1526655 36800.0 False \n1526656 30000.0 False \n1526657 30000.0 False \n1526658 39400.0 False \n\n person_housetype pmts_pmtsoverdue_635A_max pmts_dpdvalue_108P_over31 \n0 None 36.426704 None \n1 None 36.426704 None \n2 None 36.426704 None \n3 None 36.426704 None \n4 None 36.426704 None \n... ... ... ... \n1526654 OWNED 36.426704 None \n1526655 None 36.426704 None \n1526656 None 36.426704 None \n1526657 None 36.426704 None \n1526658 None 36.426704 None \n\n[1526655 rows x 45 columns]\n","output_type":"stream"}]},{"cell_type":"code","source":"pd_df_filtered.isnull().sum()","metadata":{"execution":{"iopub.status.busy":"2024-04-22T00:45:55.814684Z","iopub.execute_input":"2024-04-22T00:45:55.815153Z","iopub.status.idle":"2024-04-22T00:45:58.237794Z","shell.execute_reply.started":"2024-04-22T00:45:55.815116Z","shell.execute_reply":"2024-04-22T00:45:58.236185Z"},"trusted":true},"execution_count":16,"outputs":[{"execution_count":16,"output_type":"execute_result","data":{"text/plain":"case_id 0\ndate_decision 0\nMONTH 0\nWEEK_NUM 0\ntarget 0\namtinstpaidbefduel24m_4187115A 0\nannuitynextmonth_57A 0\navginstallast24m_3658937A 0\navglnamtstart24m_4525187A 0\ncurrdebtcredtyperange_828A 0\ndisbursedcredamount_1113A 0\ndownpmt_116A 0\nlastapprcommoditycat_1041M 0\nlastapprcommoditytypec_5251766M 0\nlastapprcredamount_781A 0\nlastcancelreason_561M 0\nlastotherinc_902A 0\nlastotherlnsexpense_631A 0\nlastrejectcommoditycat_161M 0\nlastrejectcommodtypec_5251769M 0\nlastrejectcredamount_222A 0\nlastrejectreason_759M 0\nlastrejectreasonclient_4145040M 0\nmaininc_215A 0\nmaxannuity_159A 0\nmaxannuity_4075009A 0\nmaxinstallast24m_3658928A 0\nmaxlnamtstart6m_4525199A 0\npreviouscontdistrict_112M 0\nprice_1097A 0\nsumoutstandtotalest_4493215A 0\ntotalsettled_863A 0\ntotinstallast1m_4525188A 0\ndescription_5085714M 26183\neducation_1103M 26183\neducation_88M 26183\nmaritalst_385M 26183\nmaritalst_893M 26183\npmtaverage_4527227A 0\npmtssum_45A 0\nmainoccupationinc_384A_max 0\nmainoccupationinc_384A_any_selfemployed 0\nperson_housetype 1425837\npmts_pmtsoverdue_635A_max 0\npmts_dpdvalue_108P_over31 1490240\ndtype: int64"},"metadata":{}}]},{"cell_type":"code","source":"columns_to_one_hot_encode = [\n 'description_5085714M', 'education_1103M', 'education_88M',\n 'maritalst_385M', 'maritalst_893M', 'person_housetype',\n 'pmts_dpdvalue_108P_over31'\n]\n\n# Perform one-hot encoding and treat NaN as a separate category\nfor column in columns_to_one_hot_encode:\n # Use get_dummies to encode the data, treating NaN as its own category\n encoded_columns = pd.get_dummies(pd_df_filtered[column], prefix=column, dummy_na=True)\n # Drop the original column as it is now encoded\n pd_df_filtered = pd_df_filtered.drop(column, axis=1)\n # Join the encoded columns to the original DataFrame\n pd_df_filtered = pd_df_filtered.join(encoded_columns)\n","metadata":{"execution":{"iopub.status.busy":"2024-04-22T00:45:58.240138Z","iopub.execute_input":"2024-04-22T00:45:58.240646Z","iopub.status.idle":"2024-04-22T00:46:05.993917Z","shell.execute_reply.started":"2024-04-22T00:45:58.240606Z","shell.execute_reply":"2024-04-22T00:46:05.992654Z"},"trusted":true},"execution_count":17,"outputs":[]},{"cell_type":"code","source":"pd_df_filtered['target'].value_counts()","metadata":{"execution":{"iopub.status.busy":"2024-04-22T00:46:05.995519Z","iopub.execute_input":"2024-04-22T00:46:05.995992Z","iopub.status.idle":"2024-04-22T00:46:06.024733Z","shell.execute_reply.started":"2024-04-22T00:46:05.995953Z","shell.execute_reply":"2024-04-22T00:46:06.022943Z"},"trusted":true},"execution_count":18,"outputs":[{"execution_count":18,"output_type":"execute_result","data":{"text/plain":"target\n0 1478661\n1 47994\nName: count, dtype: int64"},"metadata":{}}]},{"cell_type":"code","source":"# Set display options to show all rows and columns without truncation\npd.set_option('display.max_rows', None)\npd.set_option('display.max_columns', None)\npd.set_option('display.width', None)\npd.set_option('display.max_colwidth', None)\n\nnum_columns = pd_df_filtered.shape[1]\n\n# Print the number of columns\nprint(\"Number of columns:\", num_columns)\npd_df_filtered.dtypes","metadata":{"execution":{"iopub.status.busy":"2024-04-22T00:46:06.026738Z","iopub.execute_input":"2024-04-22T00:46:06.027271Z","iopub.status.idle":"2024-04-22T00:46:06.046435Z","shell.execute_reply.started":"2024-04-22T00:46:06.027229Z","shell.execute_reply":"2024-04-22T00:46:06.04526Z"},"trusted":true},"execution_count":19,"outputs":[{"name":"stdout","text":"Number of columns: 77\n","output_type":"stream"},{"execution_count":19,"output_type":"execute_result","data":{"text/plain":"case_id int64\ndate_decision object\nMONTH int64\nWEEK_NUM int64\ntarget int64\namtinstpaidbefduel24m_4187115A float64\nannuitynextmonth_57A float64\navginstallast24m_3658937A float64\navglnamtstart24m_4525187A float64\ncurrdebtcredtyperange_828A float64\ndisbursedcredamount_1113A float64\ndownpmt_116A float64\nlastapprcommoditycat_1041M object\nlastapprcommoditytypec_5251766M object\nlastapprcredamount_781A float64\nlastcancelreason_561M object\nlastotherinc_902A float64\nlastotherlnsexpense_631A float64\nlastrejectcommoditycat_161M object\nlastrejectcommodtypec_5251769M object\nlastrejectcredamount_222A float64\nlastrejectreason_759M object\nlastrejectreasonclient_4145040M object\nmaininc_215A float64\nmaxannuity_159A float64\nmaxannuity_4075009A float64\nmaxinstallast24m_3658928A float64\nmaxlnamtstart6m_4525199A float64\npreviouscontdistrict_112M object\nprice_1097A float64\nsumoutstandtotalest_4493215A float64\ntotalsettled_863A float64\ntotinstallast1m_4525188A float64\npmtaverage_4527227A float64\npmtssum_45A float64\nmainoccupationinc_384A_max float64\nmainoccupationinc_384A_any_selfemployed bool\npmts_pmtsoverdue_635A_max float64\ndescription_5085714M_2fc785b2 bool\ndescription_5085714M_a55475b1 bool\ndescription_5085714M_nan bool\neducation_1103M_39a0853f bool\neducation_1103M_6b2ae0fa bool\neducation_1103M_717ddd49 bool\neducation_1103M_a55475b1 bool\neducation_1103M_c8e1a1d0 bool\neducation_1103M_nan bool\neducation_88M_6b2ae0fa bool\neducation_88M_717ddd49 bool\neducation_88M_a34a13c8 bool\neducation_88M_a55475b1 bool\neducation_88M_c8e1a1d0 bool\neducation_88M_nan bool\nmaritalst_385M_3439d993 bool\nmaritalst_385M_38c061ee bool\nmaritalst_385M_a55475b1 bool\nmaritalst_385M_a7fcb6e5 bool\nmaritalst_385M_b6cabe76 bool\nmaritalst_385M_ecd83604 bool\nmaritalst_385M_nan bool\nmaritalst_893M_1a19667c bool\nmaritalst_893M_46b968c3 bool\nmaritalst_893M_977b2a70 bool\nmaritalst_893M_a55475b1 bool\nmaritalst_893M_e18430ff bool\nmaritalst_893M_ecd83604 bool\nmaritalst_893M_nan bool\nperson_housetype_COMPANY_FLAT bool\nperson_housetype_COOP_FLAT bool\nperson_housetype_FLAT bool\nperson_housetype_OWNED bool\nperson_housetype_PARENTAL bool\nperson_housetype_STATE_FLAT bool\nperson_housetype_nan bool\npmts_dpdvalue_108P_over31_False bool\npmts_dpdvalue_108P_over31_True bool\npmts_dpdvalue_108P_over31_nan bool\ndtype: object"},"metadata":{}}]},{"cell_type":"code","source":"pd_df = pd_df_filtered","metadata":{"execution":{"iopub.status.busy":"2024-04-22T00:46:06.047692Z","iopub.execute_input":"2024-04-22T00:46:06.048148Z","iopub.status.idle":"2024-04-22T00:46:06.059993Z","shell.execute_reply.started":"2024-04-22T00:46:06.048113Z","shell.execute_reply":"2024-04-22T00:46:06.058716Z"},"trusted":true},"execution_count":20,"outputs":[]},{"cell_type":"code","source":"#Convert date_decision to weekday and month decision\n\npd_df[\"date_decision\"] = pd.to_datetime(pd_df[\"date_decision\"]) # Ensure it's a datetime type\n\n# Create new columns for month and weekday\npd_df[\"month_decision\"] =pd_df[\"date_decision\"].dt.month\npd_df[\"weekday_decision\"] = pd_df[\"date_decision\"].dt.weekday # 0=Monday, 6=Sunday\n\npd_df.drop(columns=['date_decision','MONTH'], inplace=True)\npd_df","metadata":{"id":"SCjSqr94hazT","execution":{"iopub.status.busy":"2024-04-22T00:46:06.062851Z","iopub.execute_input":"2024-04-22T00:46:06.063477Z","iopub.status.idle":"2024-04-22T01:11:15.069649Z","shell.execute_reply.started":"2024-04-22T00:46:06.063441Z","shell.execute_reply":"2024-04-22T01:11:15.067199Z"},"trusted":true},"execution_count":21,"outputs":[{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)","Cell \u001b[0;32mIn[21], line 10\u001b[0m\n\u001b[1;32m 7\u001b[0m pd_df[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mweekday_decision\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m pd_df[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdate_decision\u001b[39m\u001b[38;5;124m\"\u001b[39m]\u001b[38;5;241m.\u001b[39mdt\u001b[38;5;241m.\u001b[39mweekday \u001b[38;5;66;03m# 0=Monday, 6=Sunday\u001b[39;00m\n\u001b[1;32m 9\u001b[0m pd_df\u001b[38;5;241m.\u001b[39mdrop(columns\u001b[38;5;241m=\u001b[39m[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdate_decision\u001b[39m\u001b[38;5;124m'\u001b[39m,\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mMONTH\u001b[39m\u001b[38;5;124m'\u001b[39m], inplace\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[0;32m---> 10\u001b[0m pd_df\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/IPython/core/displayhook.py:268\u001b[0m, in \u001b[0;36mDisplayHook.__call__\u001b[0;34m(self, result)\u001b[0m\n\u001b[1;32m 266\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstart_displayhook()\n\u001b[1;32m 267\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mwrite_output_prompt()\n\u001b[0;32m--> 268\u001b[0m format_dict, md_dict \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcompute_format_data\u001b[49m\u001b[43m(\u001b[49m\u001b[43mresult\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 269\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mupdate_user_ns(result)\n\u001b[1;32m 270\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfill_exec_result(result)\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/IPython/core/displayhook.py:157\u001b[0m, in \u001b[0;36mDisplayHook.compute_format_data\u001b[0;34m(self, result)\u001b[0m\n\u001b[1;32m 127\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mcompute_format_data\u001b[39m(\u001b[38;5;28mself\u001b[39m, result):\n\u001b[1;32m 128\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Compute format data of the object to be displayed.\u001b[39;00m\n\u001b[1;32m 129\u001b[0m \n\u001b[1;32m 130\u001b[0m \u001b[38;5;124;03m The format data is a generalization of the :func:`repr` of an object.\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 155\u001b[0m \n\u001b[1;32m 156\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m--> 157\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mshell\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdisplay_formatter\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mformat\u001b[49m\u001b[43m(\u001b[49m\u001b[43mresult\u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/IPython/core/formatters.py:179\u001b[0m, in \u001b[0;36mDisplayFormatter.format\u001b[0;34m(self, obj, include, exclude)\u001b[0m\n\u001b[1;32m 177\u001b[0m md \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 178\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 179\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[43mformatter\u001b[49m\u001b[43m(\u001b[49m\u001b[43mobj\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 180\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m:\n\u001b[1;32m 181\u001b[0m \u001b[38;5;66;03m# FIXME: log the exception\u001b[39;00m\n\u001b[1;32m 182\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/decorator.py:232\u001b[0m, in \u001b[0;36mdecorate..fun\u001b[0;34m(*args, **kw)\u001b[0m\n\u001b[1;32m 230\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m kwsyntax:\n\u001b[1;32m 231\u001b[0m args, kw \u001b[38;5;241m=\u001b[39m fix(args, kw, sig)\n\u001b[0;32m--> 232\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mcaller\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfunc\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mextras\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[43margs\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkw\u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/IPython/core/formatters.py:223\u001b[0m, in \u001b[0;36mcatch_format_error\u001b[0;34m(method, self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 221\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"show traceback on failed format call\"\"\"\u001b[39;00m\n\u001b[1;32m 222\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 223\u001b[0m r \u001b[38;5;241m=\u001b[39m \u001b[43mmethod\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 224\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mNotImplementedError\u001b[39;00m:\n\u001b[1;32m 225\u001b[0m \u001b[38;5;66;03m# don't warn on NotImplementedErrors\u001b[39;00m\n\u001b[1;32m 226\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_check_return(\u001b[38;5;28;01mNone\u001b[39;00m, args[\u001b[38;5;241m0\u001b[39m])\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/IPython/core/formatters.py:708\u001b[0m, in \u001b[0;36mPlainTextFormatter.__call__\u001b[0;34m(self, obj)\u001b[0m\n\u001b[1;32m 701\u001b[0m stream \u001b[38;5;241m=\u001b[39m StringIO()\n\u001b[1;32m 702\u001b[0m printer \u001b[38;5;241m=\u001b[39m pretty\u001b[38;5;241m.\u001b[39mRepresentationPrinter(stream, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mverbose,\n\u001b[1;32m 703\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmax_width, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mnewline,\n\u001b[1;32m 704\u001b[0m max_seq_length\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmax_seq_length,\n\u001b[1;32m 705\u001b[0m singleton_pprinters\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msingleton_printers,\n\u001b[1;32m 706\u001b[0m type_pprinters\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtype_printers,\n\u001b[1;32m 707\u001b[0m deferred_pprinters\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdeferred_printers)\n\u001b[0;32m--> 708\u001b[0m \u001b[43mprinter\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpretty\u001b[49m\u001b[43m(\u001b[49m\u001b[43mobj\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 709\u001b[0m printer\u001b[38;5;241m.\u001b[39mflush()\n\u001b[1;32m 710\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m stream\u001b[38;5;241m.\u001b[39mgetvalue()\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/IPython/lib/pretty.py:410\u001b[0m, in \u001b[0;36mRepresentationPrinter.pretty\u001b[0;34m(self, obj)\u001b[0m\n\u001b[1;32m 407\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m meth(obj, \u001b[38;5;28mself\u001b[39m, cycle)\n\u001b[1;32m 408\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mcls\u001b[39m \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mobject\u001b[39m \\\n\u001b[1;32m 409\u001b[0m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mcallable\u001b[39m(\u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__dict__\u001b[39m\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m__repr__\u001b[39m\u001b[38;5;124m'\u001b[39m)):\n\u001b[0;32m--> 410\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_repr_pprint\u001b[49m\u001b[43m(\u001b[49m\u001b[43mobj\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcycle\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 412\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m _default_pprint(obj, \u001b[38;5;28mself\u001b[39m, cycle)\n\u001b[1;32m 413\u001b[0m \u001b[38;5;28;01mfinally\u001b[39;00m:\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/IPython/lib/pretty.py:778\u001b[0m, in \u001b[0;36m_repr_pprint\u001b[0;34m(obj, p, cycle)\u001b[0m\n\u001b[1;32m 776\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"A pprint that just redirects to the normal repr function.\"\"\"\u001b[39;00m\n\u001b[1;32m 777\u001b[0m \u001b[38;5;66;03m# Find newlines and replace them with p.break_()\u001b[39;00m\n\u001b[0;32m--> 778\u001b[0m output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mrepr\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mobj\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 779\u001b[0m lines \u001b[38;5;241m=\u001b[39m output\u001b[38;5;241m.\u001b[39msplitlines()\n\u001b[1;32m 780\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m p\u001b[38;5;241m.\u001b[39mgroup():\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pandas/core/frame.py:1214\u001b[0m, in \u001b[0;36mDataFrame.__repr__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 1211\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m buf\u001b[38;5;241m.\u001b[39mgetvalue()\n\u001b[1;32m 1213\u001b[0m repr_params \u001b[38;5;241m=\u001b[39m fmt\u001b[38;5;241m.\u001b[39mget_dataframe_repr_params()\n\u001b[0;32m-> 1214\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mto_string\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mrepr_params\u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pandas/util/_decorators.py:333\u001b[0m, in \u001b[0;36mdeprecate_nonkeyword_arguments..decorate..wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 327\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(args) \u001b[38;5;241m>\u001b[39m num_allow_args:\n\u001b[1;32m 328\u001b[0m warnings\u001b[38;5;241m.\u001b[39mwarn(\n\u001b[1;32m 329\u001b[0m msg\u001b[38;5;241m.\u001b[39mformat(arguments\u001b[38;5;241m=\u001b[39m_format_argument_list(allow_args)),\n\u001b[1;32m 330\u001b[0m \u001b[38;5;167;01mFutureWarning\u001b[39;00m,\n\u001b[1;32m 331\u001b[0m stacklevel\u001b[38;5;241m=\u001b[39mfind_stack_level(),\n\u001b[1;32m 332\u001b[0m )\n\u001b[0;32m--> 333\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pandas/core/frame.py:1394\u001b[0m, in \u001b[0;36mDataFrame.to_string\u001b[0;34m(self, buf, columns, col_space, header, index, na_rep, formatters, float_format, sparsify, index_names, justify, max_rows, max_cols, show_dimensions, decimal, line_width, min_rows, max_colwidth, encoding)\u001b[0m\n\u001b[1;32m 1375\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m option_context(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdisplay.max_colwidth\u001b[39m\u001b[38;5;124m\"\u001b[39m, max_colwidth):\n\u001b[1;32m 1376\u001b[0m formatter \u001b[38;5;241m=\u001b[39m fmt\u001b[38;5;241m.\u001b[39mDataFrameFormatter(\n\u001b[1;32m 1377\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 1378\u001b[0m columns\u001b[38;5;241m=\u001b[39mcolumns,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1392\u001b[0m decimal\u001b[38;5;241m=\u001b[39mdecimal,\n\u001b[1;32m 1393\u001b[0m )\n\u001b[0;32m-> 1394\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfmt\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mDataFrameRenderer\u001b[49m\u001b[43m(\u001b[49m\u001b[43mformatter\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mto_string\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1395\u001b[0m \u001b[43m \u001b[49m\u001b[43mbuf\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mbuf\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1396\u001b[0m \u001b[43m \u001b[49m\u001b[43mencoding\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mencoding\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1397\u001b[0m \u001b[43m \u001b[49m\u001b[43mline_width\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mline_width\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1398\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pandas/io/formats/format.py:962\u001b[0m, in \u001b[0;36mDataFrameRenderer.to_string\u001b[0;34m(self, buf, encoding, line_width)\u001b[0m\n\u001b[1;32m 959\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mpandas\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mio\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mformats\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mstring\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m StringFormatter\n\u001b[1;32m 961\u001b[0m string_formatter \u001b[38;5;241m=\u001b[39m StringFormatter(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfmt, line_width\u001b[38;5;241m=\u001b[39mline_width)\n\u001b[0;32m--> 962\u001b[0m string \u001b[38;5;241m=\u001b[39m \u001b[43mstring_formatter\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mto_string\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 963\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m save_to_buffer(string, buf\u001b[38;5;241m=\u001b[39mbuf, encoding\u001b[38;5;241m=\u001b[39mencoding)\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pandas/io/formats/string.py:29\u001b[0m, in \u001b[0;36mStringFormatter.to_string\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 28\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mto_string\u001b[39m(\u001b[38;5;28mself\u001b[39m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m \u001b[38;5;28mstr\u001b[39m:\n\u001b[0;32m---> 29\u001b[0m text \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_get_string_representation\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 30\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfmt\u001b[38;5;241m.\u001b[39mshould_show_dimensions:\n\u001b[1;32m 31\u001b[0m text \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mtext\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfmt\u001b[38;5;241m.\u001b[39mdimensions_info\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pandas/io/formats/string.py:51\u001b[0m, in \u001b[0;36mStringFormatter._get_string_representation\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 48\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39madj\u001b[38;5;241m.\u001b[39madjoin(\u001b[38;5;241m1\u001b[39m, \u001b[38;5;241m*\u001b[39mstrcols)\n\u001b[1;32m 50\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_need_to_wrap_around:\n\u001b[0;32m---> 51\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_join_multiline\u001b[49m\u001b[43m(\u001b[49m\u001b[43mstrcols\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 53\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_fit_strcols_to_terminal_width(strcols)\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pandas/io/formats/string.py:149\u001b[0m, in \u001b[0;36mStringFormatter._join_multiline\u001b[0;34m(self, strcols_input)\u001b[0m\n\u001b[1;32m 147\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 148\u001b[0m row\u001b[38;5;241m.\u001b[39mappend([\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m \u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m*\u001b[39m nrows)\n\u001b[0;32m--> 149\u001b[0m str_lst\u001b[38;5;241m.\u001b[39mappend(\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43madj\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43madjoin\u001b[49m\u001b[43m(\u001b[49m\u001b[43madjoin_width\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mrow\u001b[49m\u001b[43m)\u001b[49m)\n\u001b[1;32m 150\u001b[0m start \u001b[38;5;241m=\u001b[39m end\n\u001b[1;32m 151\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;241m.\u001b[39mjoin(str_lst)\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pandas/io/formats/printing.py:525\u001b[0m, in \u001b[0;36m_TextAdjustment.adjoin\u001b[0;34m(self, space, *lists, **kwargs)\u001b[0m\n\u001b[1;32m 524\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21madjoin\u001b[39m(\u001b[38;5;28mself\u001b[39m, space: \u001b[38;5;28mint\u001b[39m, \u001b[38;5;241m*\u001b[39mlists, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m \u001b[38;5;28mstr\u001b[39m:\n\u001b[0;32m--> 525\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43madjoin\u001b[49m\u001b[43m(\u001b[49m\u001b[43mspace\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mlists\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstrlen\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mlen\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mjustfunc\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mjustify\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pandas/io/formats/printing.py:58\u001b[0m, in \u001b[0;36madjoin\u001b[0;34m(space, *lists, **kwargs)\u001b[0m\n\u001b[1;32m 56\u001b[0m nl \u001b[38;5;241m=\u001b[39m justfunc(lst, lengths[i], mode\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mleft\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 57\u001b[0m nl \u001b[38;5;241m=\u001b[39m ([\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m \u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m*\u001b[39m lengths[i]] \u001b[38;5;241m*\u001b[39m (maxLen \u001b[38;5;241m-\u001b[39m \u001b[38;5;28mlen\u001b[39m(lst))) \u001b[38;5;241m+\u001b[39m nl\n\u001b[0;32m---> 58\u001b[0m \u001b[43mnewLists\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mappend\u001b[49m\u001b[43m(\u001b[49m\u001b[43mnl\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 59\u001b[0m toJoin \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mzip\u001b[39m(\u001b[38;5;241m*\u001b[39mnewLists)\n\u001b[1;32m 60\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;241m.\u001b[39mjoin(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;241m.\u001b[39mjoin(lines) \u001b[38;5;28;01mfor\u001b[39;00m lines \u001b[38;5;129;01min\u001b[39;00m toJoin)\n","\u001b[0;31mKeyboardInterrupt\u001b[0m: "],"ename":"KeyboardInterrupt","evalue":"","output_type":"error"}]},{"cell_type":"code","source":"len(pd_df.columns)","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"N1-GTyM_NhTe","outputId":"b8d61ce6-f820-4cb7-ff46-eab698b73f36","execution":{"iopub.status.busy":"2024-04-22T01:12:42.014188Z","iopub.execute_input":"2024-04-22T01:12:42.014642Z","iopub.status.idle":"2024-04-22T01:12:42.024209Z","shell.execute_reply.started":"2024-04-22T01:12:42.014613Z","shell.execute_reply":"2024-04-22T01:12:42.022462Z"},"trusted":true},"execution_count":22,"outputs":[{"execution_count":22,"output_type":"execute_result","data":{"text/plain":"77"},"metadata":{}}]},{"cell_type":"code","source":"pd_df.columns","metadata":{"execution":{"iopub.status.busy":"2024-04-22T01:12:43.635779Z","iopub.execute_input":"2024-04-22T01:12:43.636318Z","iopub.status.idle":"2024-04-22T01:12:43.646657Z","shell.execute_reply.started":"2024-04-22T01:12:43.636284Z","shell.execute_reply":"2024-04-22T01:12:43.645613Z"},"trusted":true},"execution_count":23,"outputs":[{"execution_count":23,"output_type":"execute_result","data":{"text/plain":"Index(['case_id', 'WEEK_NUM', 'target', 'amtinstpaidbefduel24m_4187115A',\n 'annuitynextmonth_57A', 'avginstallast24m_3658937A',\n 'avglnamtstart24m_4525187A', 'currdebtcredtyperange_828A',\n 'disbursedcredamount_1113A', 'downpmt_116A',\n 'lastapprcommoditycat_1041M', 'lastapprcommoditytypec_5251766M',\n 'lastapprcredamount_781A', 'lastcancelreason_561M', 'lastotherinc_902A',\n 'lastotherlnsexpense_631A', 'lastrejectcommoditycat_161M',\n 'lastrejectcommodtypec_5251769M', 'lastrejectcredamount_222A',\n 'lastrejectreason_759M', 'lastrejectreasonclient_4145040M',\n 'maininc_215A', 'maxannuity_159A', 'maxannuity_4075009A',\n 'maxinstallast24m_3658928A', 'maxlnamtstart6m_4525199A',\n 'previouscontdistrict_112M', 'price_1097A',\n 'sumoutstandtotalest_4493215A', 'totalsettled_863A',\n 'totinstallast1m_4525188A', 'pmtaverage_4527227A', 'pmtssum_45A',\n 'mainoccupationinc_384A_max', 'mainoccupationinc_384A_any_selfemployed',\n 'pmts_pmtsoverdue_635A_max', 'description_5085714M_2fc785b2',\n 'description_5085714M_a55475b1', 'description_5085714M_nan',\n 'education_1103M_39a0853f', 'education_1103M_6b2ae0fa',\n 'education_1103M_717ddd49', 'education_1103M_a55475b1',\n 'education_1103M_c8e1a1d0', 'education_1103M_nan',\n 'education_88M_6b2ae0fa', 'education_88M_717ddd49',\n 'education_88M_a34a13c8', 'education_88M_a55475b1',\n 'education_88M_c8e1a1d0', 'education_88M_nan',\n 'maritalst_385M_3439d993', 'maritalst_385M_38c061ee',\n 'maritalst_385M_a55475b1', 'maritalst_385M_a7fcb6e5',\n 'maritalst_385M_b6cabe76', 'maritalst_385M_ecd83604',\n 'maritalst_385M_nan', 'maritalst_893M_1a19667c',\n 'maritalst_893M_46b968c3', 'maritalst_893M_977b2a70',\n 'maritalst_893M_a55475b1', 'maritalst_893M_e18430ff',\n 'maritalst_893M_ecd83604', 'maritalst_893M_nan',\n 'person_housetype_COMPANY_FLAT', 'person_housetype_COOP_FLAT',\n 'person_housetype_FLAT', 'person_housetype_OWNED',\n 'person_housetype_PARENTAL', 'person_housetype_STATE_FLAT',\n 'person_housetype_nan', 'pmts_dpdvalue_108P_over31_False',\n 'pmts_dpdvalue_108P_over31_True', 'pmts_dpdvalue_108P_over31_nan',\n 'month_decision', 'weekday_decision'],\n dtype='object')"},"metadata":{}}]},{"cell_type":"code","source":"pd_df.head(5)","metadata":{"execution":{"iopub.status.busy":"2024-04-22T01:12:46.326597Z","iopub.execute_input":"2024-04-22T01:12:46.327011Z","iopub.status.idle":"2024-04-22T01:12:46.400854Z","shell.execute_reply.started":"2024-04-22T01:12:46.326982Z","shell.execute_reply":"2024-04-22T01:12:46.399397Z"},"trusted":true},"execution_count":24,"outputs":[{"execution_count":24,"output_type":"execute_result","data":{"text/plain":" case_id WEEK_NUM target amtinstpaidbefduel24m_4187115A \\\n0 0 0 0 55958.371939 \n1 1 0 0 55958.371939 \n2 2 0 0 55958.371939 \n3 3 0 0 55958.371939 \n4 4 0 1 55958.371939 \n\n annuitynextmonth_57A avginstallast24m_3658937A avglnamtstart24m_4525187A \\\n0 0.0 5401.590717 44717.566753 \n1 0.0 5401.590717 44717.566753 \n2 0.0 5401.590717 44717.566753 \n3 0.0 5401.590717 44717.566753 \n4 0.0 5401.590717 44717.566753 \n\n currdebtcredtyperange_828A disbursedcredamount_1113A downpmt_116A \\\n0 0.0 30000.0 0.0 \n1 0.0 19999.8 0.0 \n2 0.0 78000.0 0.0 \n3 0.0 40000.0 0.0 \n4 0.0 44000.0 0.0 \n\n lastapprcommoditycat_1041M lastapprcommoditytypec_5251766M \\\n0 a55475b1 a55475b1 \n1 a55475b1 a55475b1 \n2 a55475b1 a55475b1 \n3 a55475b1 a55475b1 \n4 a55475b1 a55475b1 \n\n lastapprcredamount_781A lastcancelreason_561M lastotherinc_902A \\\n0 36890.370898 a55475b1 782.262163 \n1 36890.370898 a55475b1 782.262163 \n2 36890.370898 a55475b1 782.262163 \n3 36890.370898 P94_109_143 782.262163 \n4 36890.370898 P24_27_36 782.262163 \n\n lastotherlnsexpense_631A lastrejectcommoditycat_161M \\\n0 9367.174166 a55475b1 \n1 9367.174166 a55475b1 \n2 9367.174166 a55475b1 \n3 9367.174166 a55475b1 \n4 9367.174166 a55475b1 \n\n lastrejectcommodtypec_5251769M lastrejectcredamount_222A \\\n0 a55475b1 51049.111779 \n1 a55475b1 51049.111779 \n2 a55475b1 10000.000000 \n3 a55475b1 59999.800000 \n4 a55475b1 51049.111779 \n\n lastrejectreason_759M lastrejectreasonclient_4145040M maininc_215A \\\n0 a55475b1 a55475b1 49485.688836 \n1 a55475b1 a55475b1 49485.688836 \n2 a55475b1 a55475b1 49485.688836 \n3 P94_109_143 a55475b1 49485.688836 \n4 a55475b1 a55475b1 49485.688836 \n\n maxannuity_159A maxannuity_4075009A maxinstallast24m_3658928A \\\n0 0.0 41559.724362 15394.124674 \n1 0.0 41559.724362 15394.124674 \n2 0.0 41559.724362 15394.124674 \n3 0.0 41559.724362 15394.124674 \n4 0.0 41559.724362 15394.124674 \n\n maxlnamtstart6m_4525199A previouscontdistrict_112M price_1097A \\\n0 44908.606292 a55475b1 34464.999507 \n1 44908.606292 a55475b1 34464.999507 \n2 44908.606292 a55475b1 34464.999507 \n3 44908.606292 a55475b1 34464.999507 \n4 44908.606292 a55475b1 34464.999507 \n\n sumoutstandtotalest_4493215A totalsettled_863A totinstallast1m_4525188A \\\n0 28309.777969 0.0 10411.377565 \n1 28309.777969 0.0 10411.377565 \n2 28309.777969 0.0 10411.377565 \n3 28309.777969 0.0 10411.377565 \n4 28309.777969 0.0 10411.377565 \n\n pmtaverage_4527227A pmtssum_45A mainoccupationinc_384A_max \\\n0 10033.556094 13199.93597 10800.0 \n1 10033.556094 13199.93597 10000.0 \n2 10033.556094 13199.93597 14000.0 \n3 10033.556094 13199.93597 10000.0 \n4 10033.556094 13199.93597 24000.0 \n\n mainoccupationinc_384A_any_selfemployed pmts_pmtsoverdue_635A_max \\\n0 False 36.426704 \n1 False 36.426704 \n2 False 36.426704 \n3 False 36.426704 \n4 False 36.426704 \n\n description_5085714M_2fc785b2 description_5085714M_a55475b1 \\\n0 False False \n1 False False \n2 False False \n3 False False \n4 False False \n\n description_5085714M_nan education_1103M_39a0853f \\\n0 True False \n1 True False \n2 True False \n3 True False \n4 True False \n\n education_1103M_6b2ae0fa education_1103M_717ddd49 \\\n0 False False \n1 False False \n2 False False \n3 False False \n4 False False \n\n education_1103M_a55475b1 education_1103M_c8e1a1d0 education_1103M_nan \\\n0 False False True \n1 False False True \n2 False False True \n3 False False True \n4 False False True \n\n education_88M_6b2ae0fa education_88M_717ddd49 education_88M_a34a13c8 \\\n0 False False False \n1 False False False \n2 False False False \n3 False False False \n4 False False False \n\n education_88M_a55475b1 education_88M_c8e1a1d0 education_88M_nan \\\n0 False False True \n1 False False True \n2 False False True \n3 False False True \n4 False False True \n\n maritalst_385M_3439d993 maritalst_385M_38c061ee maritalst_385M_a55475b1 \\\n0 False False False \n1 False False False \n2 False False False \n3 False False False \n4 False False False \n\n maritalst_385M_a7fcb6e5 maritalst_385M_b6cabe76 maritalst_385M_ecd83604 \\\n0 False False False \n1 False False False \n2 False False False \n3 False False False \n4 False False False \n\n maritalst_385M_nan maritalst_893M_1a19667c maritalst_893M_46b968c3 \\\n0 True False False \n1 True False False \n2 True False False \n3 True False False \n4 True False False \n\n maritalst_893M_977b2a70 maritalst_893M_a55475b1 maritalst_893M_e18430ff \\\n0 False False False \n1 False False False \n2 False False False \n3 False False False \n4 False False False \n\n maritalst_893M_ecd83604 maritalst_893M_nan person_housetype_COMPANY_FLAT \\\n0 False True False \n1 False True False \n2 False True False \n3 False True False \n4 False True False \n\n person_housetype_COOP_FLAT person_housetype_FLAT person_housetype_OWNED \\\n0 False False False \n1 False False False \n2 False False False \n3 False False False \n4 False False False \n\n person_housetype_PARENTAL person_housetype_STATE_FLAT \\\n0 False False \n1 False False \n2 False False \n3 False False \n4 False False \n\n person_housetype_nan pmts_dpdvalue_108P_over31_False \\\n0 True False \n1 True False \n2 True False \n3 True False \n4 True False \n\n pmts_dpdvalue_108P_over31_True pmts_dpdvalue_108P_over31_nan \\\n0 False True \n1 False True \n2 False True \n3 False True \n4 False True \n\n month_decision weekday_decision \n0 1 3 \n1 1 3 \n2 1 4 \n3 1 3 \n4 1 4 ","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
case_idWEEK_NUMtargetamtinstpaidbefduel24m_4187115Aannuitynextmonth_57Aavginstallast24m_3658937Aavglnamtstart24m_4525187Acurrdebtcredtyperange_828Adisbursedcredamount_1113Adownpmt_116Alastapprcommoditycat_1041Mlastapprcommoditytypec_5251766Mlastapprcredamount_781Alastcancelreason_561Mlastotherinc_902Alastotherlnsexpense_631Alastrejectcommoditycat_161Mlastrejectcommodtypec_5251769Mlastrejectcredamount_222Alastrejectreason_759Mlastrejectreasonclient_4145040Mmaininc_215Amaxannuity_159Amaxannuity_4075009Amaxinstallast24m_3658928Amaxlnamtstart6m_4525199Apreviouscontdistrict_112Mprice_1097Asumoutstandtotalest_4493215Atotalsettled_863Atotinstallast1m_4525188Apmtaverage_4527227Apmtssum_45Amainoccupationinc_384A_maxmainoccupationinc_384A_any_selfemployedpmts_pmtsoverdue_635A_maxdescription_5085714M_2fc785b2description_5085714M_a55475b1description_5085714M_naneducation_1103M_39a0853feducation_1103M_6b2ae0faeducation_1103M_717ddd49education_1103M_a55475b1education_1103M_c8e1a1d0education_1103M_naneducation_88M_6b2ae0faeducation_88M_717ddd49education_88M_a34a13c8education_88M_a55475b1education_88M_c8e1a1d0education_88M_nanmaritalst_385M_3439d993maritalst_385M_38c061eemaritalst_385M_a55475b1maritalst_385M_a7fcb6e5maritalst_385M_b6cabe76maritalst_385M_ecd83604maritalst_385M_nanmaritalst_893M_1a19667cmaritalst_893M_46b968c3maritalst_893M_977b2a70maritalst_893M_a55475b1maritalst_893M_e18430ffmaritalst_893M_ecd83604maritalst_893M_nanperson_housetype_COMPANY_FLATperson_housetype_COOP_FLATperson_housetype_FLATperson_housetype_OWNEDperson_housetype_PARENTALperson_housetype_STATE_FLATperson_housetype_nanpmts_dpdvalue_108P_over31_Falsepmts_dpdvalue_108P_over31_Truepmts_dpdvalue_108P_over31_nanmonth_decisionweekday_decision
000055958.3719390.05401.59071744717.5667530.030000.00.0a55475b1a55475b136890.370898a55475b1782.2621639367.174166a55475b1a55475b151049.111779a55475b1a55475b149485.6888360.041559.72436215394.12467444908.606292a55475b134464.99950728309.7779690.010411.37756510033.55609413199.9359710800.0False36.426704FalseFalseTrueFalseFalseFalseFalseFalseTrueFalseFalseFalseFalseFalseTrueFalseFalseFalseFalseFalseFalseTrueFalseFalseFalseFalseFalseFalseTrueFalseFalseFalseFalseFalseFalseTrueFalseFalseTrue13
110055958.3719390.05401.59071744717.5667530.019999.80.0a55475b1a55475b136890.370898a55475b1782.2621639367.174166a55475b1a55475b151049.111779a55475b1a55475b149485.6888360.041559.72436215394.12467444908.606292a55475b134464.99950728309.7779690.010411.37756510033.55609413199.9359710000.0False36.426704FalseFalseTrueFalseFalseFalseFalseFalseTrueFalseFalseFalseFalseFalseTrueFalseFalseFalseFalseFalseFalseTrueFalseFalseFalseFalseFalseFalseTrueFalseFalseFalseFalseFalseFalseTrueFalseFalseTrue13
220055958.3719390.05401.59071744717.5667530.078000.00.0a55475b1a55475b136890.370898a55475b1782.2621639367.174166a55475b1a55475b110000.000000a55475b1a55475b149485.6888360.041559.72436215394.12467444908.606292a55475b134464.99950728309.7779690.010411.37756510033.55609413199.9359714000.0False36.426704FalseFalseTrueFalseFalseFalseFalseFalseTrueFalseFalseFalseFalseFalseTrueFalseFalseFalseFalseFalseFalseTrueFalseFalseFalseFalseFalseFalseTrueFalseFalseFalseFalseFalseFalseTrueFalseFalseTrue14
330055958.3719390.05401.59071744717.5667530.040000.00.0a55475b1a55475b136890.370898P94_109_143782.2621639367.174166a55475b1a55475b159999.800000P94_109_143a55475b149485.6888360.041559.72436215394.12467444908.606292a55475b134464.99950728309.7779690.010411.37756510033.55609413199.9359710000.0False36.426704FalseFalseTrueFalseFalseFalseFalseFalseTrueFalseFalseFalseFalseFalseTrueFalseFalseFalseFalseFalseFalseTrueFalseFalseFalseFalseFalseFalseTrueFalseFalseFalseFalseFalseFalseTrueFalseFalseTrue13
440155958.3719390.05401.59071744717.5667530.044000.00.0a55475b1a55475b136890.370898P24_27_36782.2621639367.174166a55475b1a55475b151049.111779a55475b1a55475b149485.6888360.041559.72436215394.12467444908.606292a55475b134464.99950728309.7779690.010411.37756510033.55609413199.9359724000.0False36.426704FalseFalseTrueFalseFalseFalseFalseFalseTrueFalseFalseFalseFalseFalseTrueFalseFalseFalseFalseFalseFalseTrueFalseFalseFalseFalseFalseFalseTrueFalseFalseFalseFalseFalseFalseTrueFalseFalseTrue14
\n
"},"metadata":{}}]},{"cell_type":"code","source":"pd_df.isnull().sum()","metadata":{"execution":{"iopub.status.busy":"2024-04-22T01:13:06.22715Z","iopub.execute_input":"2024-04-22T01:13:06.227576Z","iopub.status.idle":"2024-04-22T01:13:07.664939Z","shell.execute_reply.started":"2024-04-22T01:13:06.227547Z","shell.execute_reply":"2024-04-22T01:13:07.663991Z"},"trusted":true},"execution_count":25,"outputs":[{"execution_count":25,"output_type":"execute_result","data":{"text/plain":"case_id 0\nWEEK_NUM 0\ntarget 0\namtinstpaidbefduel24m_4187115A 0\nannuitynextmonth_57A 0\navginstallast24m_3658937A 0\navglnamtstart24m_4525187A 0\ncurrdebtcredtyperange_828A 0\ndisbursedcredamount_1113A 0\ndownpmt_116A 0\nlastapprcommoditycat_1041M 0\nlastapprcommoditytypec_5251766M 0\nlastapprcredamount_781A 0\nlastcancelreason_561M 0\nlastotherinc_902A 0\nlastotherlnsexpense_631A 0\nlastrejectcommoditycat_161M 0\nlastrejectcommodtypec_5251769M 0\nlastrejectcredamount_222A 0\nlastrejectreason_759M 0\nlastrejectreasonclient_4145040M 0\nmaininc_215A 0\nmaxannuity_159A 0\nmaxannuity_4075009A 0\nmaxinstallast24m_3658928A 0\nmaxlnamtstart6m_4525199A 0\npreviouscontdistrict_112M 0\nprice_1097A 0\nsumoutstandtotalest_4493215A 0\ntotalsettled_863A 0\ntotinstallast1m_4525188A 0\npmtaverage_4527227A 0\npmtssum_45A 0\nmainoccupationinc_384A_max 0\nmainoccupationinc_384A_any_selfemployed 0\npmts_pmtsoverdue_635A_max 0\ndescription_5085714M_2fc785b2 0\ndescription_5085714M_a55475b1 0\ndescription_5085714M_nan 0\neducation_1103M_39a0853f 0\neducation_1103M_6b2ae0fa 0\neducation_1103M_717ddd49 0\neducation_1103M_a55475b1 0\neducation_1103M_c8e1a1d0 0\neducation_1103M_nan 0\neducation_88M_6b2ae0fa 0\neducation_88M_717ddd49 0\neducation_88M_a34a13c8 0\neducation_88M_a55475b1 0\neducation_88M_c8e1a1d0 0\neducation_88M_nan 0\nmaritalst_385M_3439d993 0\nmaritalst_385M_38c061ee 0\nmaritalst_385M_a55475b1 0\nmaritalst_385M_a7fcb6e5 0\nmaritalst_385M_b6cabe76 0\nmaritalst_385M_ecd83604 0\nmaritalst_385M_nan 0\nmaritalst_893M_1a19667c 0\nmaritalst_893M_46b968c3 0\nmaritalst_893M_977b2a70 0\nmaritalst_893M_a55475b1 0\nmaritalst_893M_e18430ff 0\nmaritalst_893M_ecd83604 0\nmaritalst_893M_nan 0\nperson_housetype_COMPANY_FLAT 0\nperson_housetype_COOP_FLAT 0\nperson_housetype_FLAT 0\nperson_housetype_OWNED 0\nperson_housetype_PARENTAL 0\nperson_housetype_STATE_FLAT 0\nperson_housetype_nan 0\npmts_dpdvalue_108P_over31_False 0\npmts_dpdvalue_108P_over31_True 0\npmts_dpdvalue_108P_over31_nan 0\nmonth_decision 0\nweekday_decision 0\ndtype: int64"},"metadata":{}}]},{"cell_type":"code","source":"pd_df.dtypes","metadata":{"execution":{"iopub.status.busy":"2024-04-22T01:13:11.772719Z","iopub.execute_input":"2024-04-22T01:13:11.773232Z","iopub.status.idle":"2024-04-22T01:13:11.787646Z","shell.execute_reply.started":"2024-04-22T01:13:11.773199Z","shell.execute_reply":"2024-04-22T01:13:11.786132Z"},"trusted":true},"execution_count":26,"outputs":[{"execution_count":26,"output_type":"execute_result","data":{"text/plain":"case_id int64\nWEEK_NUM int64\ntarget int64\namtinstpaidbefduel24m_4187115A float64\nannuitynextmonth_57A float64\navginstallast24m_3658937A float64\navglnamtstart24m_4525187A float64\ncurrdebtcredtyperange_828A float64\ndisbursedcredamount_1113A float64\ndownpmt_116A float64\nlastapprcommoditycat_1041M object\nlastapprcommoditytypec_5251766M object\nlastapprcredamount_781A float64\nlastcancelreason_561M object\nlastotherinc_902A float64\nlastotherlnsexpense_631A float64\nlastrejectcommoditycat_161M object\nlastrejectcommodtypec_5251769M object\nlastrejectcredamount_222A float64\nlastrejectreason_759M object\nlastrejectreasonclient_4145040M object\nmaininc_215A float64\nmaxannuity_159A float64\nmaxannuity_4075009A float64\nmaxinstallast24m_3658928A float64\nmaxlnamtstart6m_4525199A float64\npreviouscontdistrict_112M object\nprice_1097A float64\nsumoutstandtotalest_4493215A float64\ntotalsettled_863A float64\ntotinstallast1m_4525188A float64\npmtaverage_4527227A float64\npmtssum_45A float64\nmainoccupationinc_384A_max float64\nmainoccupationinc_384A_any_selfemployed bool\npmts_pmtsoverdue_635A_max float64\ndescription_5085714M_2fc785b2 bool\ndescription_5085714M_a55475b1 bool\ndescription_5085714M_nan bool\neducation_1103M_39a0853f bool\neducation_1103M_6b2ae0fa bool\neducation_1103M_717ddd49 bool\neducation_1103M_a55475b1 bool\neducation_1103M_c8e1a1d0 bool\neducation_1103M_nan bool\neducation_88M_6b2ae0fa bool\neducation_88M_717ddd49 bool\neducation_88M_a34a13c8 bool\neducation_88M_a55475b1 bool\neducation_88M_c8e1a1d0 bool\neducation_88M_nan bool\nmaritalst_385M_3439d993 bool\nmaritalst_385M_38c061ee bool\nmaritalst_385M_a55475b1 bool\nmaritalst_385M_a7fcb6e5 bool\nmaritalst_385M_b6cabe76 bool\nmaritalst_385M_ecd83604 bool\nmaritalst_385M_nan bool\nmaritalst_893M_1a19667c bool\nmaritalst_893M_46b968c3 bool\nmaritalst_893M_977b2a70 bool\nmaritalst_893M_a55475b1 bool\nmaritalst_893M_e18430ff bool\nmaritalst_893M_ecd83604 bool\nmaritalst_893M_nan bool\nperson_housetype_COMPANY_FLAT bool\nperson_housetype_COOP_FLAT bool\nperson_housetype_FLAT bool\nperson_housetype_OWNED bool\nperson_housetype_PARENTAL bool\nperson_housetype_STATE_FLAT bool\nperson_housetype_nan bool\npmts_dpdvalue_108P_over31_False bool\npmts_dpdvalue_108P_over31_True bool\npmts_dpdvalue_108P_over31_nan bool\nmonth_decision int32\nweekday_decision int32\ndtype: object"},"metadata":{}}]},{"cell_type":"code","source":"from sklearn.preprocessing import LabelEncoder\n\ncols = pd_df.select_dtypes(include=['category', 'object']).columns\n\nfor col in cols:\n le = LabelEncoder()\n pd_df[col] = le.fit_transform(pd_df[col])","metadata":{"execution":{"iopub.status.busy":"2024-04-22T01:13:14.649965Z","iopub.execute_input":"2024-04-22T01:13:14.650444Z","iopub.status.idle":"2024-04-22T01:13:18.029345Z","shell.execute_reply.started":"2024-04-22T01:13:14.65041Z","shell.execute_reply":"2024-04-22T01:13:18.027812Z"},"trusted":true},"execution_count":27,"outputs":[]},{"cell_type":"code","source":"pd_df.isnull().sum()","metadata":{"execution":{"iopub.status.busy":"2024-04-22T01:13:20.264476Z","iopub.execute_input":"2024-04-22T01:13:20.264936Z","iopub.status.idle":"2024-04-22T01:13:20.412774Z","shell.execute_reply.started":"2024-04-22T01:13:20.264887Z","shell.execute_reply":"2024-04-22T01:13:20.411931Z"},"trusted":true},"execution_count":28,"outputs":[{"execution_count":28,"output_type":"execute_result","data":{"text/plain":"case_id 0\nWEEK_NUM 0\ntarget 0\namtinstpaidbefduel24m_4187115A 0\nannuitynextmonth_57A 0\navginstallast24m_3658937A 0\navglnamtstart24m_4525187A 0\ncurrdebtcredtyperange_828A 0\ndisbursedcredamount_1113A 0\ndownpmt_116A 0\nlastapprcommoditycat_1041M 0\nlastapprcommoditytypec_5251766M 0\nlastapprcredamount_781A 0\nlastcancelreason_561M 0\nlastotherinc_902A 0\nlastotherlnsexpense_631A 0\nlastrejectcommoditycat_161M 0\nlastrejectcommodtypec_5251769M 0\nlastrejectcredamount_222A 0\nlastrejectreason_759M 0\nlastrejectreasonclient_4145040M 0\nmaininc_215A 0\nmaxannuity_159A 0\nmaxannuity_4075009A 0\nmaxinstallast24m_3658928A 0\nmaxlnamtstart6m_4525199A 0\npreviouscontdistrict_112M 0\nprice_1097A 0\nsumoutstandtotalest_4493215A 0\ntotalsettled_863A 0\ntotinstallast1m_4525188A 0\npmtaverage_4527227A 0\npmtssum_45A 0\nmainoccupationinc_384A_max 0\nmainoccupationinc_384A_any_selfemployed 0\npmts_pmtsoverdue_635A_max 0\ndescription_5085714M_2fc785b2 0\ndescription_5085714M_a55475b1 0\ndescription_5085714M_nan 0\neducation_1103M_39a0853f 0\neducation_1103M_6b2ae0fa 0\neducation_1103M_717ddd49 0\neducation_1103M_a55475b1 0\neducation_1103M_c8e1a1d0 0\neducation_1103M_nan 0\neducation_88M_6b2ae0fa 0\neducation_88M_717ddd49 0\neducation_88M_a34a13c8 0\neducation_88M_a55475b1 0\neducation_88M_c8e1a1d0 0\neducation_88M_nan 0\nmaritalst_385M_3439d993 0\nmaritalst_385M_38c061ee 0\nmaritalst_385M_a55475b1 0\nmaritalst_385M_a7fcb6e5 0\nmaritalst_385M_b6cabe76 0\nmaritalst_385M_ecd83604 0\nmaritalst_385M_nan 0\nmaritalst_893M_1a19667c 0\nmaritalst_893M_46b968c3 0\nmaritalst_893M_977b2a70 0\nmaritalst_893M_a55475b1 0\nmaritalst_893M_e18430ff 0\nmaritalst_893M_ecd83604 0\nmaritalst_893M_nan 0\nperson_housetype_COMPANY_FLAT 0\nperson_housetype_COOP_FLAT 0\nperson_housetype_FLAT 0\nperson_housetype_OWNED 0\nperson_housetype_PARENTAL 0\nperson_housetype_STATE_FLAT 0\nperson_housetype_nan 0\npmts_dpdvalue_108P_over31_False 0\npmts_dpdvalue_108P_over31_True 0\npmts_dpdvalue_108P_over31_nan 0\nmonth_decision 0\nweekday_decision 0\ndtype: int64"},"metadata":{}}]},{"cell_type":"code","source":"len(pd_df.columns)","metadata":{"execution":{"iopub.status.busy":"2024-04-22T01:13:23.940199Z","iopub.execute_input":"2024-04-22T01:13:23.940756Z","iopub.status.idle":"2024-04-22T01:13:23.94932Z","shell.execute_reply.started":"2024-04-22T01:13:23.940717Z","shell.execute_reply":"2024-04-22T01:13:23.947958Z"},"trusted":true},"execution_count":29,"outputs":[{"execution_count":29,"output_type":"execute_result","data":{"text/plain":"77"},"metadata":{}}]},{"cell_type":"code","source":"from imblearn.over_sampling import SMOTE\nfrom sklearn.model_selection import train_test_split\n\n\nX = pd_df.drop('target', axis=1)\ny = pd_df['target']\n\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, stratify=y, random_state=42)\nX_valid, X_test, y_valid, y_test = train_test_split(X_test, y_test, test_size=0.5, stratify=y_test, random_state=42)\n\n\nsmote = SMOTE(random_state=42)\n\n\nX_train_smote, y_train_smote = smote.fit_resample(X_train, y_train)\nX_valid_smote, y_valid_smote = smote.fit_resample(X_valid, y_valid)\nX_test_smote, y_test_smote = smote.fit_resample(X_test, y_test)\n\n# Checking the new class distribution\nprint(pd.Series(y_train_smote).value_counts())\n\n# Combining the features and target columns to create complete datasets\ndf_train = pd.concat([X_train_smote, y_train_smote], axis=1) # Full training set\ndf_valid = pd.concat([X_valid_smote, y_valid_smote], axis=1) # Full validation set\ndf_test = pd.concat([X_test_smote, y_test_smote], axis=1) # Full test set\n\n# Optional: Check class distribution in the new datasets\nprint(\"Train class distribution:\")\nprint(df_train['target'].value_counts())\nprint(\"Validation class distribution:\")\nprint(df_valid['target'].value_counts())\nprint(\"Test class distribution:\")\nprint(df_test['target'].value_counts())","metadata":{"id":"7r71r31uhazT","execution":{"iopub.status.busy":"2024-04-22T05:16:02.456591Z","iopub.execute_input":"2024-04-22T05:16:02.456992Z","iopub.status.idle":"2024-04-22T05:16:02.894806Z","shell.execute_reply.started":"2024-04-22T05:16:02.45696Z","shell.execute_reply":"2024-04-22T05:16:02.89325Z"},"trusted":true},"execution_count":3,"outputs":[{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)","Cell \u001b[0;32mIn[3], line 5\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mimblearn\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mover_sampling\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m SMOTE\n\u001b[1;32m 2\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01msklearn\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mmodel_selection\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m train_test_split\n\u001b[0;32m----> 5\u001b[0m X \u001b[38;5;241m=\u001b[39m \u001b[43mpd_df\u001b[49m\u001b[38;5;241m.\u001b[39mdrop(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtarget\u001b[39m\u001b[38;5;124m'\u001b[39m, axis\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1\u001b[39m)\n\u001b[1;32m 6\u001b[0m y \u001b[38;5;241m=\u001b[39m pd_df[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtarget\u001b[39m\u001b[38;5;124m'\u001b[39m]\n\u001b[1;32m 8\u001b[0m X_train, X_test, y_train, y_test \u001b[38;5;241m=\u001b[39m train_test_split(X, y, test_size\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m0.3\u001b[39m, stratify\u001b[38;5;241m=\u001b[39my, random_state\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m42\u001b[39m)\n","\u001b[0;31mNameError\u001b[0m: name 'pd_df' is not defined"],"ename":"NameError","evalue":"name 'pd_df' is not defined","output_type":"error"}]},{"cell_type":"markdown","source":"#**Training Models**\n\nIn this section, we are going to train several ensemble models and apply cross validation to select the best model based on performance.\n\n* LightGBM\n* XGboost\n* CatBoost\n* AdaBoost\n* HistGradientBoostingClassifier\n* SVM\n","metadata":{"id":"r20H2IcmxR_D"}},{"cell_type":"markdown","source":"## LightGBM","metadata":{}},{"cell_type":"code","source":"import lightgbm as lgb\nlgb_train = lgb.Dataset(X_train_smote, label=y_train_smote)\nlgb_valid = lgb.Dataset(X_valid_smote, label=y_valid_smote, reference=lgb_train)\n\nparams = {\n \"boosting_type\": \"gbdt\", # Gradient boosting decision tree algorithm\n \"objective\": \"binary\", # Binary log loss classification (binary classification problem)\n \"metric\": \"auc\", # The metric to be used for validation data is AUC (Area Under Curve)\n \"max_depth\": 6, # Maximum tree depth for base learners\n \"num_leaves\": 40, # Maximum tree leaves for base learners\n \"learning_rate\": 0.01, # Boosting learning rate\n \"feature_fraction\": 0.8, # Subsample ratio of columns when constructing each tree\n \"bagging_fraction\": 0.7, # Subsample ratio of the training instance (prevents overfitting)\n \"bagging_freq\": 5, # Frequency for bagging (k means perform bagging at every k iteration)\n \"n_estimators\": 2050, # Number of boosted trees to fit\n \"verbose\": -1, # Controls the level of LightGBM's verbosity (less verbose)\n \"min_child_samples\": 30, # Minimum number of data needed in a child (leaf)\n \"min_split_gain\": 0.1, # Minimum loss reduction required to make a further partition on a leaf node of the tree\n \"reg_alpha\": 0.51, # L1 regularization term on weights (increases model's generalization)\n \"reg_lambda\": 0.5 # L2 regularization term on weights (prevents overfitting)\n}\n\n\ngbm = lgb.train(\n params,\n lgb_train,\n valid_sets=lgb_valid,\n callbacks=[lgb.log_evaluation(50)]\n)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import GroupKFold, StratifiedGroupKFold\nimport lightgbm as lgb\nX = df_train.drop(columns=[\"target\", \"case_id\", \"WEEK_NUM\"])\ny = df_train[\"target\"]\nweeks = df_train[\"WEEK_NUM\"]\n\ncv = StratifiedGroupKFold(n_splits=5, shuffle=False)\n\nparams = {\n \"boosting_type\": \"gbdt\",\n \"objective\": \"binary\",\n \"metric\": \"auc\",\n \"max_depth\": 10, \n \"learning_rate\": 0.05,\n \"n_estimators\": 2000, \n \"colsample_bytree\": 0.8,\n \"colsample_bynode\": 0.8,\n \"verbose\": -1,\n \"random_state\": 42,\n \"reg_alpha\": 0.1,\n \"reg_lambda\": 10,\n \"extra_trees\":True,\n 'num_leaves':64, \n \"verbose\": -1,\n}\n\nfitted_models = []\nbest_model = None\nauc_scores_light = []\nmodel_filename = \"best_lightgbm_model.joblib\"\n\n\nfor idx_train, idx_valid in cv.split(X, y, groups=weeks):\n X_train, y_train = X.iloc[idx_train], y.iloc[idx_train]\n X_valid, y_valid = X.iloc[idx_valid], y.iloc[idx_valid]\n \n model = lgb.LGBMClassifier(**params)\n model.fit(\n X_train, y_train,\n eval_set = [(X_valid, y_valid)],\n callbacks = [lgb.log_evaluation(200), lgb.early_stopping(60)] )\n fitted_models.append(model)\n \n y_pred_valid = model.predict_proba(X_valid)[:,1]\n auc_score = roc_auc_score(y_valid, y_pred_valid)\n auc_scores_light.append(auc_score)\n \nprint(\"CV AUC scores: \", auc_scores_light)\nprint(\"Maximum CV AUC score: \", max(auc_scores_light))\n\n# Check if this fold's AUC is the best\n if auc > best_auc:\n best_auc = auc\n best_model = model # Store the best model\n # Save the best model to a file\n if best_model:\n joblib.dump(best_model, model_filename) # Save the best model","metadata":{"execution":{"iopub.status.busy":"2024-04-22T01:16:31.463327Z","iopub.execute_input":"2024-04-22T01:16:31.464571Z","iopub.status.idle":"2024-04-22T03:41:15.543074Z","shell.execute_reply.started":"2024-04-22T01:16:31.464533Z","shell.execute_reply":"2024-04-22T03:41:15.540917Z"},"trusted":true},"execution_count":31,"outputs":[{"name":"stdout","text":"Training until validation scores don't improve for 60 rounds\n[200]\tvalid_0's auc: 0.966148\n[400]\tvalid_0's auc: 0.972297\n[600]\tvalid_0's auc: 0.975275\n[800]\tvalid_0's auc: 0.976949\n[1000]\tvalid_0's auc: 0.978289\n[1200]\tvalid_0's auc: 0.979295\n[1400]\tvalid_0's auc: 0.980047\n[1600]\tvalid_0's auc: 0.980693\n[1800]\tvalid_0's auc: 0.981155\n[2000]\tvalid_0's auc: 0.981522\nDid not meet early stopping. Best iteration is:\n[1999]\tvalid_0's auc: 0.981522\nTraining until validation scores don't improve for 60 rounds\n[200]\tvalid_0's auc: 0.968077\n[400]\tvalid_0's auc: 0.973743\n[600]\tvalid_0's auc: 0.976642\n[800]\tvalid_0's auc: 0.978411\n[1000]\tvalid_0's auc: 0.9796\n[1200]\tvalid_0's auc: 0.980547\n[1400]\tvalid_0's auc: 0.981224\n[1600]\tvalid_0's auc: 0.981764\n[1800]\tvalid_0's auc: 0.982254\n[2000]\tvalid_0's auc: 0.982644\nDid not meet early stopping. Best iteration is:\n[2000]\tvalid_0's auc: 0.982644\nTraining until validation scores don't improve for 60 rounds\n[200]\tvalid_0's auc: 0.969118\n[400]\tvalid_0's auc: 0.974691\n[600]\tvalid_0's auc: 0.977323\n[800]\tvalid_0's auc: 0.979059\n[1000]\tvalid_0's auc: 0.980174\n[1200]\tvalid_0's auc: 0.980982\n[1400]\tvalid_0's auc: 0.981627\n[1600]\tvalid_0's auc: 0.982157\n[1800]\tvalid_0's auc: 0.982574\n[2000]\tvalid_0's auc: 0.982989\nDid not meet early stopping. Best iteration is:\n[2000]\tvalid_0's auc: 0.982989\nTraining until validation scores don't improve for 60 rounds\n[200]\tvalid_0's auc: 0.968779\n[400]\tvalid_0's auc: 0.974009\n[600]\tvalid_0's auc: 0.976533\n[800]\tvalid_0's auc: 0.978146\n[1000]\tvalid_0's auc: 0.979276\n[1200]\tvalid_0's auc: 0.980093\n[1400]\tvalid_0's auc: 0.980713\n[1600]\tvalid_0's auc: 0.981234\n[1800]\tvalid_0's auc: 0.981712\n[2000]\tvalid_0's auc: 0.982047\nDid not meet early stopping. Best iteration is:\n[2000]\tvalid_0's auc: 0.982047\nTraining until validation scores don't improve for 60 rounds\n[200]\tvalid_0's auc: 0.959163\n[400]\tvalid_0's auc: 0.966329\n[600]\tvalid_0's auc: 0.969613\n[800]\tvalid_0's auc: 0.971745\n[1000]\tvalid_0's auc: 0.973211\n[1200]\tvalid_0's auc: 0.974378\n[1400]\tvalid_0's auc: 0.975291\n[1600]\tvalid_0's auc: 0.976081\n[1800]\tvalid_0's auc: 0.976677\n[2000]\tvalid_0's auc: 0.977164\nDid not meet early stopping. Best iteration is:\n[2000]\tvalid_0's auc: 0.977164\n","output_type":"stream"},{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)","Cell \u001b[0;32mIn[31], line 46\u001b[0m\n\u001b[1;32m 43\u001b[0m auc_score \u001b[38;5;241m=\u001b[39m roc_auc_score(y_valid, y_pred_valid)\n\u001b[1;32m 44\u001b[0m auc_scores_light\u001b[38;5;241m.\u001b[39mappend(auc_score)\n\u001b[0;32m---> 46\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCV AUC scores: \u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[43mcv_scores\u001b[49m)\n\u001b[1;32m 47\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mMaximum CV AUC score: \u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28mmax\u001b[39m(cv_scores))\n","\u001b[0;31mNameError\u001b[0m: name 'cv_scores' is not defined"],"ename":"NameError","evalue":"name 'cv_scores' is not defined","output_type":"error"}]},{"cell_type":"code","source":"print(\"Maximum CV AUC score: \", max(auc_scores_light))","metadata":{"execution":{"iopub.status.busy":"2024-04-22T04:12:22.404838Z","iopub.execute_input":"2024-04-22T04:12:22.405973Z","iopub.status.idle":"2024-04-22T04:12:22.414484Z","shell.execute_reply.started":"2024-04-22T04:12:22.40593Z","shell.execute_reply":"2024-04-22T04:12:22.412834Z"},"trusted":true},"execution_count":33,"outputs":[{"name":"stdout","text":"Maximum CV AUC score: 0.9829892414109191\n","output_type":"stream"}]},{"cell_type":"code","source":"# Plot the AUC scores for each fold\nplt.plot(range(1, 6), auc_scores_light, marker='o', linestyle='-', color='b')\nplt.title(\"AUC for each Cross-Validation Fold\")\nplt.xlabel(\"Fold\")\nplt.ylabel(\"AUC\")\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-04-22T04:32:29.468153Z","iopub.execute_input":"2024-04-22T04:32:29.470554Z","iopub.status.idle":"2024-04-22T04:32:30.203182Z","shell.execute_reply.started":"2024-04-22T04:32:29.470475Z","shell.execute_reply":"2024-04-22T04:32:30.201223Z"},"trusted":true},"execution_count":54,"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}}]},{"cell_type":"code","source":"import joblib\nfrom sklearn.metrics import roc_auc_score\n\n# Load the best model from the saved file\nbest_model = joblib.load(\"best_lightgbm_model.joblib\")\n\n# Use the model to predict on the untrained data\npredictions_test = best_model.predict(X_test_smote)\n\n# Calculate AUC score on the test set\nauc_test = roc_auc_score(y_test_smote, predictions_test)\n\nprint(f\"Test AUC: {auc_test}\")","metadata":{"execution":{"iopub.status.busy":"2024-04-22T05:24:52.787835Z","iopub.execute_input":"2024-04-22T05:24:52.788812Z","iopub.status.idle":"2024-04-22T05:24:52.865968Z","shell.execute_reply.started":"2024-04-22T05:24:52.788775Z","shell.execute_reply":"2024-04-22T05:24:52.864566Z"},"trusted":true},"execution_count":4,"outputs":[{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mFileNotFoundError\u001b[0m Traceback (most recent call last)","Cell \u001b[0;32mIn[4], line 5\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01msklearn\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mmetrics\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m roc_auc_score\n\u001b[1;32m 4\u001b[0m \u001b[38;5;66;03m# Load the best model from the saved file\u001b[39;00m\n\u001b[0;32m----> 5\u001b[0m best_model \u001b[38;5;241m=\u001b[39m \u001b[43mjoblib\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mload\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mbest_lightgbm_model.joblib\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 7\u001b[0m \u001b[38;5;66;03m# Use the model to predict on the untrained data\u001b[39;00m\n\u001b[1;32m 8\u001b[0m predictions_test \u001b[38;5;241m=\u001b[39m best_model\u001b[38;5;241m.\u001b[39mpredict(X_test_smote)\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/joblib/numpy_pickle.py:650\u001b[0m, in \u001b[0;36mload\u001b[0;34m(filename, mmap_mode)\u001b[0m\n\u001b[1;32m 648\u001b[0m obj \u001b[38;5;241m=\u001b[39m _unpickle(fobj)\n\u001b[1;32m 649\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 650\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28;43mopen\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mfilename\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mrb\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mas\u001b[39;00m f:\n\u001b[1;32m 651\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m _read_fileobject(f, filename, mmap_mode) \u001b[38;5;28;01mas\u001b[39;00m fobj:\n\u001b[1;32m 652\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(fobj, \u001b[38;5;28mstr\u001b[39m):\n\u001b[1;32m 653\u001b[0m \u001b[38;5;66;03m# if the returned file object is a string, this means we\u001b[39;00m\n\u001b[1;32m 654\u001b[0m \u001b[38;5;66;03m# try to load a pickle file generated with an version of\u001b[39;00m\n\u001b[1;32m 655\u001b[0m \u001b[38;5;66;03m# Joblib so we load it with joblib compatibility function.\u001b[39;00m\n","\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: 'best_lightgbm_model.joblib'"],"ename":"FileNotFoundError","evalue":"[Errno 2] No such file or directory: 'best_lightgbm_model.joblib'","output_type":"error"}]},{"cell_type":"markdown","source":"# Submission","metadata":{}},{"cell_type":"code","source":"from sklearn.base import BaseEstimator, RegressorMixin\nclass VotingModel(BaseEstimator, RegressorMixin):\n def __init__(self, estimators):\n super().__init__()\n self.estimators = estimators\n \n def fit(self, X, y=None):\n return self\n \n def predict(self, X):\n y_preds = [estimator.predict(X) for estimator in self.estimators]\n return np.mean(y_preds, axis=0)\n \n def predict_proba(self, X):\n \n y_preds = [estimator.predict_proba(X) for estimator in self.estimators[:5]]\n \n X[cat_cols] = X[cat_cols].astype(\"category\")\n y_preds += [estimator.predict_proba(X) for estimator in self.estimators[5:10]]\n y_preds+=y_preds #tang trong so\n y_preds += [estimator.predict_proba(X) for estimator in self.estimators[10:]]\n print(len(y_preds))\n return np.mean(y_preds, axis=0)\n\nmodel = VotingModel(fitted_models)","metadata":{"execution":{"iopub.status.busy":"2024-04-22T05:26:03.864189Z","iopub.execute_input":"2024-04-22T05:26:03.864982Z","iopub.status.idle":"2024-04-22T05:26:03.899055Z","shell.execute_reply.started":"2024-04-22T05:26:03.864949Z","shell.execute_reply":"2024-04-22T05:26:03.897782Z"},"trusted":true},"execution_count":6,"outputs":[{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)","Cell \u001b[0;32mIn[6], line 25\u001b[0m\n\u001b[1;32m 22\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;28mlen\u001b[39m(y_preds))\n\u001b[1;32m 23\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m np\u001b[38;5;241m.\u001b[39mmean(y_preds, axis\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m0\u001b[39m)\n\u001b[0;32m---> 25\u001b[0m model \u001b[38;5;241m=\u001b[39m VotingModel(\u001b[43mfitted_models\u001b[49m)\n","\u001b[0;31mNameError\u001b[0m: name 'fitted_models' is not defined"],"ename":"NameError","evalue":"name 'fitted_models' is not defined","output_type":"error"}]},{"cell_type":"code","source":"df_test = df_test.drop(columns=[\"WEEK_NUM\"])\ndf_test = df_test.set_index(\"case_id\")","metadata":{"execution":{"iopub.status.busy":"2024-04-22T05:09:24.941561Z","iopub.execute_input":"2024-04-22T05:09:24.942017Z","iopub.status.idle":"2024-04-22T05:09:24.996085Z","shell.execute_reply.started":"2024-04-22T05:09:24.941986Z","shell.execute_reply":"2024-04-22T05:09:24.994011Z"},"trusted":true},"execution_count":67,"outputs":[{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mKeyError\u001b[0m Traceback (most recent call last)","\u001b[0;32m/tmp/ipykernel_33/631971335.py\u001b[0m in \u001b[0;36m?\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;31m#X_test_smote = X_test_smote.drop(columns=[\"case_id\", \"WEEK_NUM\"])\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mX_test_smote\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mX_test_smote\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mset_index\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"case_id\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0mlgb_pred\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mSeries\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict_proba\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX_test_smote\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mX_test_smote\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mindex\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.10/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36m?\u001b[0;34m(self, keys, drop, append, inplace, verify_integrity)\u001b[0m\n\u001b[1;32m 6118\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mfound\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 6119\u001b[0m \u001b[0mmissing\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcol\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 6120\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 6121\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mmissing\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 6122\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mf\"None of {missing} are in the columns\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 6123\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 6124\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0minplace\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 6125\u001b[0m \u001b[0mframe\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;31mKeyError\u001b[0m: \"None of ['case_id'] are in the columns\""],"ename":"KeyError","evalue":"\"None of ['case_id'] are in the columns\"","output_type":"error"}]},{"cell_type":"code","source":"ROOT = '/kaggle/input/home-credit-credit-risk-model-stability'\n\ny_pred = pd.Series(model.predict_proba(df_test)[:, 1], index=df_test.index)\n\ndf_subm = pd.read_csv(ROOT / \"sample_submission.csv\")\ndf_subm = df_subm.set_index(\"case_id\")\n\ndf_subm[\"score\"] = y_pred\ndf_subm.to_csv(\"submission.csv\")\ndf_subm","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}