{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","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":30635,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"from itertools import combinations\nimport optuna","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:48:10.830740Z","iopub.execute_input":"2024-03-17T19:48:10.831409Z","iopub.status.idle":"2024-03-17T19:48:11.249307Z","shell.execute_reply.started":"2024-03-17T19:48:10.831369Z","shell.execute_reply":"2024-03-17T19:48:11.248167Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{"execution":{"iopub.status.busy":"2024-03-17T19:48:11.255058Z","iopub.execute_input":"2024-03-17T19:48:11.255812Z","iopub.status.idle":"2024-03-17T19:48:12.940319Z","shell.execute_reply.started":"2024-03-17T19:48:11.255771Z","shell.execute_reply":"2024-03-17T19:48:12.939475Z"},"trusted":true},"execution_count":null,"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":{"execution":{"iopub.status.busy":"2024-03-17T19:48:12.941384Z","iopub.execute_input":"2024-03-17T19:48:12.941687Z","iopub.status.idle":"2024-03-17T19:48:12.949022Z","shell.execute_reply.started":"2024-03-17T19:48:12.941660Z","shell.execute_reply":"2024-03-17T19:48:12.948045Z"},"trusted":true},"execution_count":null,"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":{"execution":{"iopub.status.busy":"2024-03-17T19:48:12.952317Z","iopub.execute_input":"2024-03-17T19:48:12.952881Z","iopub.status.idle":"2024-03-17T19:48:26.573818Z","shell.execute_reply.started":"2024-03-17T19:48:12.952841Z","shell.execute_reply":"2024-03-17T19:48:26.572983Z"},"trusted":true},"execution_count":null,"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":{"execution":{"iopub.status.busy":"2024-03-17T19:48:26.574685Z","iopub.execute_input":"2024-03-17T19:48:26.574968Z","iopub.status.idle":"2024-03-17T19:48:26.617043Z","shell.execute_reply.started":"2024-03-17T19:48:26.574933Z","shell.execute_reply":"2024-03-17T19:48:26.616066Z"},"trusted":true},"execution_count":null,"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":{}},{"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":{"execution":{"iopub.status.busy":"2024-03-17T19:48:26.619799Z","iopub.execute_input":"2024-03-17T19:48:26.620128Z","iopub.status.idle":"2024-03-17T19:48:28.240825Z","shell.execute_reply.started":"2024-03-17T19:48:26.620100Z","shell.execute_reply":"2024-03-17T19:48:28.239932Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{"execution":{"iopub.status.busy":"2024-03-17T19:48:28.242009Z","iopub.execute_input":"2024-03-17T19:48:28.242336Z","iopub.status.idle":"2024-03-17T19:48:28.255781Z","shell.execute_reply.started":"2024-03-17T19:48:28.242308Z","shell.execute_reply":"2024-03-17T19:48:28.254787Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"case_ids = data[\"case_id\"].unique().shuffle(seed=1)\ncase_ids_train, case_ids_test = train_test_split(case_ids, train_size=0.6, random_state=1)\ncase_ids_valid, case_ids_test = train_test_split(case_ids_test, train_size=0.5, random_state=1)\n\ncols_pred = []\nfor col in data.columns:\n    if col[-1].isupper() and col[:-1].islower():\n        cols_pred.append(col)\n\nprint(cols_pred)\n\ndef from_polars_to_pandas(case_ids: pl.DataFrame) -> pl.DataFrame:\n    return (\n        data.filter(pl.col(\"case_id\").is_in(case_ids))[[\"case_id\", \"WEEK_NUM\", \"target\"]].to_pandas(),\n        data.filter(pl.col(\"case_id\").is_in(case_ids))[cols_pred].to_pandas(),\n        data.filter(pl.col(\"case_id\").is_in(case_ids))[\"target\"].to_pandas()\n    )\n\nbase_train, X_train, y_train = from_polars_to_pandas(case_ids_train)\nbase_valid, X_valid, y_valid = from_polars_to_pandas(case_ids_valid)\nbase_test, X_test, y_test = from_polars_to_pandas(case_ids_test)\n\nfor df in [X_train, X_valid, X_test]:\n    df = convert_strings(df)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:48:28.256883Z","iopub.execute_input":"2024-03-17T19:48:28.257804Z","iopub.status.idle":"2024-03-17T19:48:34.815497Z","shell.execute_reply.started":"2024-03-17T19:48:28.257751Z","shell.execute_reply":"2024-03-17T19:48:34.814616Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(f\"Train: {X_train.shape}\")\nprint(f\"Valid: {X_valid.shape}\")\nprint(f\"Test: {X_test.shape}\")","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:48:34.816796Z","iopub.execute_input":"2024-03-17T19:48:34.817203Z","iopub.status.idle":"2024-03-17T19:48:34.823369Z","shell.execute_reply.started":"2024-03-17T19:48:34.817163Z","shell.execute_reply":"2024-03-17T19:48:34.822338Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Тут я добавляю фичи в датасет","metadata":{}},{"cell_type":"code","source":"X_train.dtypes","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:48:34.824670Z","iopub.execute_input":"2024-03-17T19:48:34.825048Z","iopub.status.idle":"2024-03-17T19:48:34.837409Z","shell.execute_reply.started":"2024-03-17T19:48:34.825010Z","shell.execute_reply":"2024-03-17T19:48:34.836461Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Добавим логарифмические признаки со знаком.","metadata":{}},{"cell_type":"code","source":"def add_new_features(df):\n    df[\"cred_utilization_rate\"] = df[\"currdebt_22A\"] / df[\"credamount_770A\"]\n    \n    df[\"debt_to_income_ratio\"] = df[\"currdebt_22A\"] / df[\"maininc_215A\"]\n    \n    to_add = {}\n    \n    for col in df.select_dtypes(\"float64\").columns:\n        to_add[\"log_\" + col] = np.log1p(np.abs(df[col])) * np.sign(df[col])\n    \n#     cat_columns = X_train.select_dtypes(\"category\").columns\n#     df_str = df[cat_columns].astype(\"str\")\n    \n#     for a, b in combinations(cat_columns, 2):\n#         to_add[a + \"_\" + b] = df_str[a] + df_str[b]\n    \n    return pd.concat([df, pd.DataFrame(to_add)], axis = 1)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:48:34.838273Z","iopub.execute_input":"2024-03-17T19:48:34.839017Z","iopub.status.idle":"2024-03-17T19:48:34.846293Z","shell.execute_reply.started":"2024-03-17T19:48:34.838988Z","shell.execute_reply":"2024-03-17T19:48:34.845461Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train = add_new_features(X_train)\nX_valid = add_new_features(X_valid)\nX_test = add_new_features(X_test)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:48:34.847195Z","iopub.execute_input":"2024-03-17T19:48:34.847457Z","iopub.status.idle":"2024-03-17T19:48:36.798230Z","shell.execute_reply.started":"2024-03-17T19:48:34.847433Z","shell.execute_reply":"2024-03-17T19:48:36.797006Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Training LightGBM\n\nMinimal example of LightGBM training is shown below.","metadata":{}},{"cell_type":"code","source":"lgb_train = lgb.Dataset(X_train, label = y_train)\nlgb_valid = lgb.Dataset(X_valid, label = y_valid, reference = lgb_train)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:48:36.802438Z","iopub.execute_input":"2024-03-17T19:48:36.802802Z","iopub.status.idle":"2024-03-17T19:48:36.807333Z","shell.execute_reply.started":"2024-03-17T19:48:36.802771Z","shell.execute_reply":"2024-03-17T19:48:36.806643Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def objective(trial):\n    params = {\n        \"boosting_type\": \"gbdt\",\n        \"objective\": \"binary\",\n        \"metric\": \"auc\",\n        \"max_depth\": trial.suggest_int(\"max_depth\", 1, 4),\n        \"num_leaves\": trial.suggest_int(\"num_leaves\", 10, 40, step = 5),\n        \"learning_rate\": trial.suggest_float(\"learning_rate\", 1e-6, 1e-3, log = True),\n        \"feature_fraction\": trial.suggest_float(\"feature_fraction\", 0.7, 0.95),\n        \"bagging_fraction\": trial.suggest_float(\"bagging_fraction\", 0.7, 0.95),\n        \"bagging_freq\": trial.suggest_int(\"bagging_freq\", 3, 7),\n        \"verbose\": -1,\n        \"random_seed\": 14,\n        \"n_estimators\": 1000,\n    }\n    \n    gbm = lgb.train(\n        params,\n        lgb_train,\n        valid_sets = lgb_valid,\n        callbacks = [lgb.log_evaluation(50), lgb.early_stopping(50)]\n    )\n    \n    return roc_auc_score(\n        base_valid[\"target\"],\n        gbm.predict(X_valid, num_iteration = gbm.best_iteration)\n    )","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:48:36.808375Z","iopub.execute_input":"2024-03-17T19:48:36.808850Z","iopub.status.idle":"2024-03-17T19:48:36.818263Z","shell.execute_reply.started":"2024-03-17T19:48:36.808821Z","shell.execute_reply":"2024-03-17T19:48:36.817621Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"study = optuna.create_study(direction = \"maximize\")\nstudy.optimize(objective, n_trials = 50)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:48:36.819268Z","iopub.execute_input":"2024-03-17T19:48:36.819727Z","iopub.status.idle":"2024-03-17T19:52:27.951892Z","shell.execute_reply.started":"2024-03-17T19:48:36.819699Z","shell.execute_reply":"2024-03-17T19:52:27.950950Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"params = {\n    \"boosting_type\": \"gbdt\",\n    \"objective\": \"binary\",\n    \"metric\": \"auc\",\n    \"random_seed\": 14,\n    \"n_estimators\": 1000,\n}\n\nparams.update(study.best_params)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"gbm = lgb.train(\n    params,\n    lgb_train,\n    valid_sets = lgb_valid,\n    callbacks = [lgb.log_evaluation(50), lgb.early_stopping(50)]\n)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:52:27.953210Z","iopub.execute_input":"2024-03-17T19:52:27.953554Z","iopub.status.idle":"2024-03-17T19:52:44.988697Z","shell.execute_reply.started":"2024-03-17T19:52:27.953523Z","shell.execute_reply":"2024-03-17T19:52:44.987554Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Evaluation with AUC and then comparison with the stability metric is shown below.","metadata":{}},{"cell_type":"code","source":"for base, X in [(base_train, X_train), (base_valid, X_valid), (base_test, X_test)]:\n    y_pred = gbm.predict(X, num_iteration=gbm.best_iteration)\n    base[\"score\"] = y_pred\n\nprint(f'The AUC score on the train set is: {roc_auc_score(base_train[\"target\"], base_train[\"score\"])}') \nprint(f'The AUC score on the valid set is: {roc_auc_score(base_valid[\"target\"], base_valid[\"score\"])}') \nprint(f'The AUC score on the test set is: {roc_auc_score(base_test[\"target\"], base_test[\"score\"])}')  ","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:52:44.990402Z","iopub.execute_input":"2024-03-17T19:52:44.991978Z","iopub.status.idle":"2024-03-17T19:52:50.313589Z","shell.execute_reply.started":"2024-03-17T19:52:44.991924Z","shell.execute_reply":"2024-03-17T19:52:50.312414Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def gini_stability(base, w_fallingrate=88.0, w_resstd=-0.5):\n    gini_in_time = base.loc[:, [\"WEEK_NUM\", \"target\", \"score\"]]\\\n        .sort_values(\"WEEK_NUM\")\\\n        .groupby(\"WEEK_NUM\")[[\"target\", \"score\"]]\\\n        .apply(lambda x: 2*roc_auc_score(x[\"target\"], x[\"score\"])-1).tolist()\n    \n    x = np.arange(len(gini_in_time))\n    y = gini_in_time\n    a, b = np.polyfit(x, y, 1)\n    y_hat = a*x + b\n    residuals = y - y_hat\n    res_std = np.std(residuals)\n    avg_gini = np.mean(gini_in_time)\n    return avg_gini + w_fallingrate * min(0, a) + w_resstd * res_std\n\nstability_score_train = gini_stability(base_train)\nstability_score_valid = gini_stability(base_valid)\nstability_score_test = gini_stability(base_test)\n\nprint(f'The stability score on the train set is: {stability_score_train}') \nprint(f'The stability score on the valid set is: {stability_score_valid}') \nprint(f'The stability score on the test set is: {stability_score_test}')  ","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:52:50.315189Z","iopub.execute_input":"2024-03-17T19:52:50.315555Z","iopub.status.idle":"2024-03-17T19:52:51.274366Z","shell.execute_reply.started":"2024-03-17T19:52:50.315521Z","shell.execute_reply":"2024-03-17T19:52:51.272906Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Submission\n\nScoring the submission dataset is below, we need to take care of new categories. Then we save the score as a last step. ","metadata":{}},{"cell_type":"code","source":"X_submission = data_submission[cols_pred].to_pandas()\nX_submission = convert_strings(X_submission)\ncategorical_cols = X_train.select_dtypes(include=['category']).columns\n\nfor col in categorical_cols:\n    train_categories = set(X_train[col].cat.categories)\n    submission_categories = set(X_submission[col].cat.categories)\n    new_categories = submission_categories - train_categories\n    X_submission.loc[X_submission[col].isin(new_categories), col] = \"Unknown\"\n    new_dtype = pd.CategoricalDtype(categories=train_categories, ordered=True)\n    X_train[col] = X_train[col].astype(new_dtype)\n    X_submission[col] = X_submission[col].astype(new_dtype)\n\nX_submission = add_new_features(X_submission)\ny_submission_pred = gbm.predict(X_submission, num_iteration=gbm.best_iteration)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:52:51.276055Z","iopub.execute_input":"2024-03-17T19:52:51.276489Z","iopub.status.idle":"2024-03-17T19:52:51.420546Z","shell.execute_reply.started":"2024-03-17T19:52:51.276447Z","shell.execute_reply":"2024-03-17T19:52:51.419219Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission = pd.DataFrame({\n    \"case_id\": data_submission[\"case_id\"].to_numpy(),\n    \"score\": y_submission_pred\n}).set_index('case_id')\nsubmission.to_csv(\"./submission.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:52:51.421897Z","iopub.execute_input":"2024-03-17T19:52:51.422271Z","iopub.status.idle":"2024-03-17T19:52:51.432628Z","shell.execute_reply.started":"2024-03-17T19:52:51.422237Z","shell.execute_reply":"2024-03-17T19:52:51.431513Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Best of luck, and most importantly, enjoy the process of learning and discovery! \n\n<img src=\"https://i.imgur.com/obVWIBh.png\" alt=\"Image\" width=\"700\"/>","metadata":{}}]}