{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"## ***If you like my work, Kindly upvote it !!*** ","metadata":{}},{"cell_type":"markdown","source":"\n### **Note :-** \n\n#### ***Below sharing links of my other notebooks along with some sample work done by me, I hope you will like it too.. Incase you have any suggestions or add-less or guidance you want to give me, feel free to write through comment section -***","metadata":{}},{"cell_type":"markdown","source":" ***Feedback Prize - Predicting Effective Arguments :- [Student writing📖 : The Visualization📊](https://www.kaggle.com/code/deepakkaura/student-writing-the-visualization)***\n\n ***Spaceship Titanic :- [Spaceship Titanic : Story of a Space Titanic 🌌🚢](https://www.kaggle.com/code/deepakkaura/spaceship-titanic-story-of-a-space-titanic)***\n\n ***H&M Personalized Fashion Recommendations :- [H&M : Insightful Plots and Prediction](https://www.kaggle.com/code/deepakkaura/h-m-insightful-plots-and-prediction)***\n\n ***Few sample work of mine :- [Deepak Kaura's sample work](https://github.com/deepak7642/Few-Samples-of-My-work/blob/main/README.md)***","metadata":{}},{"cell_type":"markdown","source":"# ***Welcome to the Banking sector 🏦***","metadata":{}},{"cell_type":"markdown","source":"![Amex.jpg](data:image/jpeg;base64,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)","metadata":{"id":"QioZ-K9NlKLC"}},{"cell_type":"markdown","source":"# **Overview :**\n\n***Whether out at a restaurant or buying tickets to a concert, modern life counts on the convenience of a credit card to make daily purchases. It saves us from carrying large amounts of cash and also can advance a full purchase that can be paid over time. How do card issuers know we’ll pay back what we charge? That’s a complex problem with many existing solutions—and even more potential improvements, to be explored in this competition.***\n\n**Credit default prediction is central to managing risk in a consumer lending business. Credit default prediction allows lenders to optimize lending decisions, which leads to a better customer experience and sound business economics. Current models exist to help manage risk. But it's possible to create better models that can outperform those currently in use.**\n\n***American Express is a globally integrated payments company. The largest payment card issuer in the world, they provide customers with access to products, insights, and experiences that enrich lives and build business success.***\n\n**In this competition, you’ll apply your machine learning skills to predict credit default. Specifically, you will leverage an industrial scale data set to build a machine learning model that challenges the current model in production. Training, validation, and testing datasets include time-series behavioral data and anonymized customer profile information. You're free to explore any technique to create the most powerful model, from creating features to using the data in a more organic way within a model.**\n\n***If successful, you'll help create a better customer experience for cardholders by making it easier to be approved for a credit card. Top solutions could challenge the credit default prediction model used by the world's largest payment card issuer—earning you cash prizes, the opportunity to interview with American Express, and potentially a rewarding new career.***","metadata":{}},{"cell_type":"markdown","source":"## **Objective of this competition -**\n\n\n***It's to predict the probability that a customer does not pay back their credit card balance amount in the future based on their monthly customer profile. The target binary variable is calculated by observing 18 months performance window after the latest credit card statement, and if the customer does not pay due amount in 120 days after their latest statement date it is considered a default event.***","metadata":{}},{"cell_type":"markdown","source":"### **Data Description : -**\n\n\n***The objective of this competition is to predict the probability that a customer does not pay back their credit card balance amount in the future based on their monthly customer profile. The target binary variable is calculated by observing 18 months performance window after the latest credit card statement, and if the customer does not pay due amount in 120 days after their latest statement date it is considered a default event.***\n\n**The dataset contains aggregated profile features for each customer at each statement date. Features are anonymized and normalized, and fall into the following general categories:**\n\n* D_* = Delinquency variables\n* S_* = Spend variables\n* P_* = Payment variables\n* B_* = Balance variables\n* R_* = Risk variables\n\n\n***with the following features being categorical:***\n\n**['B_30', 'B_38', 'D_114', 'D_116', 'D_117', 'D_120', 'D_126', 'D_63', 'D_64', 'D_66', 'D_68']**\n\n***Your task is to predict, for each customer_ID, the probability of a future payment default (target = 1).***\n\n**Note that the negative class has been subsampled for this dataset at 5%, and thus receives a 20x weighting in the scoring metric.**\n\n\n**Files**\n\n* **train_data.csv - training data with multiple statement dates per customer_ID**\n\n* **train_labels.csv - target label for each customer_ID**\n\n* **test_data.csv - corresponding test data; your objective is to predict the target label for each customer_ID**\n\n* **sample_submission.csv - a sample submission file in the correct format**","metadata":{}},{"cell_type":"markdown","source":"# **Import Libraries**","metadata":{}},{"cell_type":"code","source":"import numpy as np \nimport pandas as pd\nimport seaborn as sns\nimport matplotlib.pyplot as plt\nimport matplotlib.colors\nimport plotly.express as px\nimport plotly.graph_objects as go\nfrom plotly.subplots import make_subplots\nfrom plotly.offline import init_notebook_mode\nimport warnings, gc","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:31:32.349116Z","iopub.execute_input":"2022-06-28T09:31:32.349677Z","iopub.status.idle":"2022-06-28T09:31:34.965420Z","shell.execute_reply.started":"2022-06-28T09:31:32.349636Z","shell.execute_reply":"2022-06-28T09:31:34.964325Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## ***Read the file***","metadata":{}},{"cell_type":"code","source":"train_df = pd.read_feather('../input/amexfeather/train_data.ftr')\n\n\ntrain_df.head()","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:08:50.793474Z","iopub.execute_input":"2022-06-28T09:08:50.793876Z","iopub.status.idle":"2022-06-28T09:09:13.411856Z","shell.execute_reply.started":"2022-06-28T09:08:50.793841Z","shell.execute_reply":"2022-06-28T09:09:13.409373Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## **Statistics description**","metadata":{}},{"cell_type":"code","source":"train_df.describe().T.drop('std',axis=1).style.background_gradient(subset=['min','50%', 'max'], cmap='winter')","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:09:59.114473Z","iopub.execute_input":"2022-06-28T09:09:59.114929Z","iopub.status.idle":"2022-06-28T09:12:45.575971Z","shell.execute_reply.started":"2022-06-28T09:09:59.114889Z","shell.execute_reply":"2022-06-28T09:12:45.575241Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_df = pd.read_feather('../input/amexfeather/test_data.ftr')\n\n\ntest_df.head()","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:13:10.413231Z","iopub.execute_input":"2022-06-28T09:13:10.413989Z","iopub.status.idle":"2022-06-28T09:13:54.432543Z","shell.execute_reply.started":"2022-06-28T09:13:10.413936Z","shell.execute_reply":"2022-06-28T09:13:54.431498Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## ***Exploratory Data Analysis***","metadata":{}},{"cell_type":"code","source":"temp=dict(layout=go.Layout(font=dict(family=\"Franklin Gothic\", size=12), \n                           height=500, width=1000))\n\n\n\ntrain_df = train_df.groupby('customer_ID').tail(1).set_index('customer_ID')\nprint(\"The training data begins on {} and ends on {}.\".format(train_df['S_2'].min().strftime('%m-%d-%Y'),train_df['S_2'].max().strftime('%m-%d-%Y')))\nprint(\"There are {:,.0f} customers in the training set and {} features.\".format(train_df.shape[0],train_df.shape[1]))\n\n\ntest_df = test_df.groupby('customer_ID').tail(1).set_index('customer_ID')\nprint(\"\\nThe test data begins on {} and ends on {}.\".format(test_df['S_2'].min().strftime('%m-%d-%Y'),test_df['S_2'].max().strftime('%m-%d-%Y')))\nprint(\"There are {:,.0f} customers in the test set and {} features.\".format(test_df.shape[0],test_df.shape[1]))\n\ndel test_df['S_2']\ngc.collect()\n\n\ntitles=['Delinquency '+str(i).split('_')[1] if i.startswith('D') else 'Spend '+str(i).split('_')[1] \n        if i.startswith('S') else 'Payment '+str(i).split('_')[1]  if i.startswith('P') \n        else 'Balance '+str(i).split('_')[1] if i.startswith('B') else \n        'Risk '+str(i).split('_')[1] for i in train_df.columns[:-1]]\ncat_cols=['Balance 30', 'Balance 38', 'Delinquency 63', 'Delinquency 64', 'Delinquency 66', 'Delinquency 68',\n          'Delinquency 114', 'Delinquency 116', 'Delinquency 117', 'Delinquency 120', 'Delinquency 126', 'Target']\ntest_df.columns=titles[1:]\ntitles.append('Target')\ntrain_df.columns=titles","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:14:11.327281Z","iopub.execute_input":"2022-06-28T09:14:11.328074Z","iopub.status.idle":"2022-06-28T09:14:20.457909Z","shell.execute_reply.started":"2022-06-28T09:14:11.328026Z","shell.execute_reply":"2022-06-28T09:14:20.456870Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"target=train_df.Target.value_counts(normalize=True)\ntarget.rename(index={1:'Default',0:'Paid'},inplace=True)\npal, color=['#a6edd3'], ['#a6edd3']\nfig=go.Figure()\nfig.add_trace(go.Pie(labels=target.index, values=target*100, hole=.45, \n                     showlegend=True,sort=False, \n                     marker=dict(colors=color,line=dict(color=pal,width=2.5)),\n                     hovertemplate = \"%{label} Accounts: %{value:.2f}%<extra></extra>\"))\nfig.update_layout(template=temp, title='Target Distribution', \n                  legend=dict(traceorder='reversed',y=1.05,x=0),\n                  uniformtext_minsize=15, uniformtext_mode='hide',width=700)\nfig.show()","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:14:30.830774Z","iopub.execute_input":"2022-06-28T09:14:30.831190Z","iopub.status.idle":"2022-06-28T09:14:30.982187Z","shell.execute_reply.started":"2022-06-28T09:14:30.831157Z","shell.execute_reply":"2022-06-28T09:14:30.981278Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**From above we saw that about 25% of customers in the training data have defaulted. This proportion is consistent across each day in the training set, with a weekly seasonal trend in the day of the month when customers receive their statements.**","metadata":{}},{"cell_type":"code","source":"plot_df=train_df.reset_index().groupby('Spend 2')['customer_ID'].nunique().reset_index()\nfig=go.Figure()\nfig.add_trace(go.Scatter(x=plot_df['Spend 2'], \n                         y=plot_df['customer_ID'], mode='lines',\n                         line=dict(color=pal[0], width=3), \n                         hovertemplate = ''))\nfig.update_layout(template=temp, title=\"Frequency of Customer Statements\", \n                  hovermode=\"x unified\", width=800,height=500,\n                  xaxis_title='Statement Date', yaxis_title='Number of Statements Issued')\nfig.show()\ndel train_df['Spend 2']","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:14:48.712682Z","iopub.execute_input":"2022-06-28T09:14:48.714059Z","iopub.status.idle":"2022-06-28T09:14:49.656294Z","shell.execute_reply.started":"2022-06-28T09:14:48.713967Z","shell.execute_reply":"2022-06-28T09:14:49.655317Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cols=[col for col in train_df.columns if (col.startswith(('D','T'))) & (col not in cat_cols[:-1])]\nplot_df=train_df[cols]","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:20:19.388273Z","iopub.execute_input":"2022-06-28T09:20:19.388759Z","iopub.status.idle":"2022-06-28T09:20:19.912205Z","shell.execute_reply.started":"2022-06-28T09:20:19.388726Z","shell.execute_reply":"2022-06-28T09:20:19.911258Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"corr=plot_df.iloc[:,:-1].corr()\nmask=np.triu(np.ones_like(corr, dtype=bool))[1:,:-1]\ncorr=corr.iloc[1:,:-1].copy()\nfig, ax = plt.subplots(figsize=(48,48))   \nsns.heatmap(corr, mask=mask, vmin=-1, vmax=1, center=0, annot=True, fmt='.2f', \n            cmap='coolwarm', annot_kws={'fontsize':10,'fontweight':'bold'}, cbar=False)\nax.tick_params(left=False,bottom=False)\nax.set_xticklabels(ax.get_xticklabels(), rotation=45, horizontalalignment='right',fontsize=12)\nax.set_yticklabels(ax.get_yticklabels(), fontsize=12)\nplt.title('Correlations between Payment Variables\\n', fontsize=16)\nfig.show()","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:20:23.536076Z","iopub.execute_input":"2022-06-28T09:20:23.537325Z","iopub.status.idle":"2022-06-28T09:20:49.309852Z","shell.execute_reply.started":"2022-06-28T09:20:23.537228Z","shell.execute_reply":"2022-06-28T09:20:49.308627Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"***There are several highly correlated Delinquency variables, with a few pairs perfectly positively correlated at 1.0. There are also a number of missing correlations, particularly in Delinquency 87, due to null values in the data. Below are the relationships between some of the most correlated Delinquency variables.***","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(1,4, figsize=(16,5))\nfig.suptitle('Relationships between Delinquency Variables,\\nLog-Transformed',fontsize=16)\nax[0].hexbin(x='Delinquency 74', y='Delinquency 75', data=plot_df, bins='log', gridsize=40, cmap='winter')\nax[0].set(xlabel='Delinquency 74',ylabel='Delinquency 75')\nax[0].text(1, 4, 'Correlation: {:.2f}'.format(plot_df[['Delinquency 74','Delinquency 75']].corr().iloc[1,0]), \n           ha=\"center\", va=\"center\",bbox=dict(boxstyle=\"round,pad=0.3\",fc=\"white\"))\nax[1].hexbin(x='Delinquency 58', y='Delinquency 74', data=plot_df, bins='log', gridsize=40, cmap='winter')\nax[1].set(xlabel='Delinquency 58',ylabel='Delinquency 74')\nax[1].text(0.3, 4.2, 'Correlation: {:.2f}'.format(plot_df[['Delinquency 58','Delinquency 74']].corr().iloc[1,0]),\n           ha=\"center\", va=\"center\",bbox=dict(boxstyle=\"round,pad=0.3\",fc=\"white\"))\nax[2].hexbin(x='Delinquency 113', y='Delinquency 115', data=plot_df, bins='log', gridsize=40, cmap='winter')\nax[2].set(xlabel='Delinquency 73',ylabel='Delinquency 137')\nax[2].text(2.15, 1.95, 'Correlation: {:.2f}'.format(plot_df[['Delinquency 113','Delinquency 115']].corr().iloc[1,0]), \n           ha=\"center\", va=\"center\",bbox=dict(boxstyle=\"round,pad=0.3\",fc=\"white\"))\nax[3].hexbin(x='Delinquency 131', y='Delinquency 132', data=plot_df, bins='log', gridsize=40, cmap='winter')\nax[3].set(xlabel='Delinquency 131',ylabel='Delinquency 132')\nax[3].text(1.1, 5.9, 'Correlation: {:.2f}'.format(plot_df[['Delinquency 131','Delinquency 132']].corr().iloc[1,0]), \n           ha=\"center\", va=\"center\",bbox=dict(boxstyle=\"round,pad=0.3\",fc=\"white\"))\nfor i in range(4):\n    ax[i].tick_params(left=False,bottom=False)\nsns.despine()\nplt.tight_layout(rect=[0, 0, 1, 0.99])\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:21:00.465472Z","iopub.execute_input":"2022-06-28T09:21:00.465897Z","iopub.status.idle":"2022-06-28T09:21:02.257147Z","shell.execute_reply.started":"2022-06-28T09:21:00.465863Z","shell.execute_reply":"2022-06-28T09:21:02.256235Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cols=[col for col in train_df.columns if (col.startswith(('S','T'))) & (col not in cat_cols[:-1])]\nplot_df=train_df[cols]","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:22:34.033664Z","iopub.execute_input":"2022-06-28T09:22:34.034077Z","iopub.status.idle":"2022-06-28T09:22:34.063604Z","shell.execute_reply.started":"2022-06-28T09:22:34.034044Z","shell.execute_reply":"2022-06-28T09:22:34.062345Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"corr=plot_df.corr()\nmask=np.triu(np.ones_like(corr, dtype=bool))[1:,:-1]\ncorr=corr.iloc[1:,:-1].copy()\nfig, ax = plt.subplots(figsize=(16,12))   \nsns.heatmap(corr, mask=mask, vmin=-1, vmax=1, center=0, annot=True, fmt='.2f', \n            cmap='winter', annot_kws={'fontsize':10,'fontweight':'bold'}, cbar=False)\nax.tick_params(left=False,bottom=False)\nax.set_xticklabels(ax.get_xticklabels(), rotation=45, horizontalalignment='right',fontsize=12)\nax.set_yticklabels(ax.get_yticklabels(), fontsize=12)\nplt.title('Correlations between Spend Variables\\n', fontsize=16)\nfig.show()","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:22:39.233572Z","iopub.execute_input":"2022-06-28T09:22:39.234084Z","iopub.status.idle":"2022-06-28T09:22:41.244370Z","shell.execute_reply.started":"2022-06-28T09:22:39.234046Z","shell.execute_reply":"2022-06-28T09:22:41.243183Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fig, ax = plt.subplots(1,4, figsize=(16,5))\nfig.suptitle('Relationships between Spend Variables,\\nLog-Transformed',fontsize=16)\nax[0].hexbin(x='Spend 24', y='Spend 22', data=plot_df, bins='log', gridsize=40, cmap='winter')\nax[0].set(xlabel='Spend 24',ylabel='Spend 22')\nax[0].text(-70, 4, 'Correlation: {:.2f}'.format(plot_df[['Spend 24','Spend 22']].corr().iloc[1,0]), \n           ha=\"center\", va=\"center\",bbox=dict(boxstyle=\"round,pad=0.3\",fc=\"white\"))\nax[1].hexbin(x='Spend 7', y='Spend 3', data=plot_df, bins='log', gridsize=40, cmap='winter')\nax[1].set(xlabel='Spend 7',ylabel='Spend 3')\nax[1].text(0.4, 4.15, 'Correlation: {:.2f}'.format(plot_df[['Spend 7','Spend 3']].corr().iloc[1,0]),\n           ha=\"center\", va=\"center\",bbox=dict(boxstyle=\"round,pad=0.3\",fc=\"white\"))\nax[2].hexbin(x='Spend 15', y='Spend 8', data=plot_df, bins='log', gridsize=40, cmap='winter')\nax[2].set(xlabel='Spend 15',ylabel='Spend 8')\nax[2].text(1.2, 1.28, 'Correlation: {:.2f}'.format(plot_df[['Spend 15','Spend 8']].corr().iloc[1,0]), \n           ha=\"center\", va=\"center\",bbox=dict(boxstyle=\"round,pad=0.3\",fc=\"white\"))\nax[3].hexbin(x='Spend 11', y='Spend 15', data=plot_df, bins='log', gridsize=40, cmap='winter')\nax[3].set(xlabel='Spend 11',ylabel='Spend 15')\nax[3].text(.5,5.5, 'Correlation: {:.2f}'.format(plot_df[['Spend 11','Spend 15']].corr().iloc[1,0]), \n           ha=\"center\", va=\"center\",bbox=dict(boxstyle=\"round,pad=0.3\",fc=\"white\"))\nfor i in range(4):\n    ax[i].tick_params(left=False,bottom=False)\nsns.despine()\nplt.tight_layout(rect=[0, 0, 1, 0.99])\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:22:48.560383Z","iopub.execute_input":"2022-06-28T09:22:48.560786Z","iopub.status.idle":"2022-06-28T09:22:50.013413Z","shell.execute_reply.started":"2022-06-28T09:22:48.560753Z","shell.execute_reply":"2022-06-28T09:22:50.012182Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cols=[col for col in train_df.columns if (col.startswith(('P','T'))) & (col not in cat_cols[:-1])]\nplot_df=train_df[cols]","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:23:32.478106Z","iopub.execute_input":"2022-06-28T09:23:32.479647Z","iopub.status.idle":"2022-06-28T09:23:32.490618Z","shell.execute_reply.started":"2022-06-28T09:23:32.479599Z","shell.execute_reply":"2022-06-28T09:23:32.489366Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"corr=plot_df.corr()\nmask=np.triu(np.ones_like(corr, dtype=bool))[1:,:-1]\ncorr=corr.iloc[1:,:-1].copy()\nfig, ax = plt.subplots(figsize=(7,5)) \nsns.heatmap(corr, mask=mask, vmin=-1, vmax=1, center=0, annot=True, fmt='.2f', \n            cmap='winter', annot_kws={'fontsize':12,'fontweight':'bold'})\nax.tick_params(left=False,bottom=False)\nax.set_xticklabels(ax.get_xticklabels(), rotation=45, horizontalalignment='right',fontsize=12)\nax.set_yticklabels(ax.get_yticklabels(), fontsize=12)\nplt.title('Correlations between Payment Variables\\n', fontsize=16)\nfig.show()","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:23:38.224148Z","iopub.execute_input":"2022-06-28T09:23:38.224645Z","iopub.status.idle":"2022-06-28T09:23:38.512134Z","shell.execute_reply.started":"2022-06-28T09:23:38.224607Z","shell.execute_reply":"2022-06-28T09:23:38.511430Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fig, ax = plt.subplots(1,3, figsize=(16,5))\nfig.suptitle('Relationships between Payment Variables,\\nLog-Transformed',fontsize=16)\nax[0].hexbin(x='Payment 2', y='Payment 3', data=plot_df, bins='log', gridsize=40, cmap='winter')\nax[0].text(-.2,2.2, 'Correlation: {:.2f}'.format(plot_df[['Payment 2','Payment 3']].corr().iloc[1,0]), \n           ha=\"center\", va=\"center\",bbox=dict(boxstyle=\"round,pad=0.3\",fc=\"white\"))\nax[0].set(xlabel='Payment 2',ylabel='Payment 3')\nax[1].hexbin(x='Payment 3', y='Payment 4', data=plot_df, bins='log', gridsize=40, cmap='winter')\nax[1].text(-.6,1.35, 'Correlation: {:.2f}'.format(plot_df[['Payment 3','Payment 4']].corr().iloc[1,0]), \n           ha=\"center\", va=\"center\",bbox=dict(boxstyle=\"round,pad=0.3\",fc=\"white\"))\nax[1].set(xlabel='Payment 3',ylabel='Payment 4')\nax[2].hexbin(x='Payment 4', y='Payment 2', data=plot_df, bins='log', gridsize=40, cmap='winter')\nax[2].text(.25,1.1, 'Correlation: {:.2f}'.format(plot_df[['Payment 4','Payment 2']].corr().iloc[1,0]), \n           ha=\"center\", va=\"center\",bbox=dict(boxstyle=\"round,pad=0.3\",fc=\"white\"))\nax[2].set(xlabel='Payment 4',ylabel='Payment 2')\nfor i in range(3):\n    ax[i].tick_params(left=False,bottom=False)\nsns.despine()\nplt.tight_layout(rect=[0, 0, 1, 0.99])\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:23:45.501425Z","iopub.execute_input":"2022-06-28T09:23:45.501821Z","iopub.status.idle":"2022-06-28T09:23:46.671992Z","shell.execute_reply.started":"2022-06-28T09:23:45.501789Z","shell.execute_reply":"2022-06-28T09:23:46.671016Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cols=[col for col in train_df.columns if (col.startswith(('B','T'))) & (col not in cat_cols[:-1])]\nplot_df=train_df[cols]","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:24:30.679641Z","iopub.execute_input":"2022-06-28T09:24:30.680040Z","iopub.status.idle":"2022-06-28T09:24:30.783845Z","shell.execute_reply.started":"2022-06-28T09:24:30.680010Z","shell.execute_reply":"2022-06-28T09:24:30.782690Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"corr=plot_df.corr()\nmask=np.triu(np.ones_like(corr, dtype=bool))[1:,:-1]\ncorr=corr.iloc[1:,:-1].copy()\nfig, ax = plt.subplots(figsize=(24,22))   \nsns.heatmap(corr, mask=mask, vmin=-1, vmax=1, center=0, annot=True, fmt='.2f', \n            cmap='winter', annot_kws={'fontsize':12,'fontweight':'bold'}, cbar=False)\nax.tick_params(left=False,bottom=False)\nax.set_xticklabels(ax.get_xticklabels(), rotation=45, horizontalalignment='right',fontsize=12)\nax.set_yticklabels(ax.get_yticklabels(), fontsize=12)\nplt.title('Correlations between Balance Variables\\n', fontsize=16)\nfig.show()","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:24:36.042297Z","iopub.execute_input":"2022-06-28T09:24:36.043596Z","iopub.status.idle":"2022-06-28T09:24:41.686143Z","shell.execute_reply.started":"2022-06-28T09:24:36.043553Z","shell.execute_reply":"2022-06-28T09:24:41.685165Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fig, ax = plt.subplots(1,3, figsize=(16,5))\nfig.suptitle('Relationships between Balance Variables,\\nLog-Transformed',fontsize=16)\nax[0].hexbin(x='Balance 23', y='Balance 7', data=plot_df, bins='log', gridsize=40, cmap='winter')\nax[0].text(.23,1.42, 'Correlation: {:.2f}'.format(plot_df[['Balance 23','Balance 7']].corr().iloc[1,0]), \n           ha=\"center\", va=\"center\",bbox=dict(boxstyle=\"round,pad=0.3\",fc=\"white\"))\nax[0].set(xlabel='Balance 23',ylabel='Balance 7')\nax[1].hexbin(x='Balance 3', y='Balance 11', data=plot_df, bins='log', gridsize=40, cmap='winter')\nax[1].text(.3,1.85, 'Correlation: {:.2f}'.format(plot_df[['Balance 3','Balance 11']].corr().iloc[1,0]), \n           ha=\"center\", va=\"center\",bbox=dict(boxstyle=\"round,pad=0.3\",fc=\"white\"))\nax[1].set(xlabel='Balance 3',ylabel='Balance 11')\nax[2].hexbin(x='Balance 11', y='Balance 2', data=plot_df, bins='log', gridsize=40, cmap='winter')\nax[2].text(.3,1.07, 'Correlation: {:.2f}'.format(plot_df[['Balance 11','Balance 2']].corr().iloc[1,0]), \n           ha=\"center\", va=\"center\",bbox=dict(boxstyle=\"round,pad=0.3\",fc=\"white\"))\nax[2].set(xlabel='Balance 11',ylabel='Balance 2')\nfor i in range(3):\n    ax[i].tick_params(left=False,bottom=False)\nsns.despine()\nplt.tight_layout(rect=[0, 0, 1, 0.99])\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:24:50.667423Z","iopub.execute_input":"2022-06-28T09:24:50.667917Z","iopub.status.idle":"2022-06-28T09:24:51.923118Z","shell.execute_reply.started":"2022-06-28T09:24:50.667878Z","shell.execute_reply":"2022-06-28T09:24:51.922140Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cols=[col for col in train_df.columns if (col.startswith(('R','T'))) & (col not in cat_cols[:-1])]\nplot_df=train_df[cols]","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:25:34.914982Z","iopub.execute_input":"2022-06-28T09:25:34.916462Z","iopub.status.idle":"2022-06-28T09:25:34.955057Z","shell.execute_reply.started":"2022-06-28T09:25:34.916396Z","shell.execute_reply":"2022-06-28T09:25:34.954062Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"corr=plot_df.corr()\nmask=np.triu(np.ones_like(corr, dtype=bool))[1:,:-1]\ncorr=corr.iloc[1:,:-1].copy()\nfig, ax = plt.subplots(figsize=(24,18))   \nsns.heatmap(corr, mask=mask, vmin=-1, vmax=1, center=0, annot=True, fmt='.2f', \n            cmap='winter', annot_kws={'fontsize':12,'fontweight':'bold'}, cbar=False)\nax.tick_params(left=False,bottom=False)\nax.set_xticklabels(ax.get_xticklabels(), rotation=45, horizontalalignment='right',fontsize=12)\nax.set_yticklabels(ax.get_yticklabels(), fontsize=12)\nplt.title('Correlations between Risk Variables\\n', fontsize=16)\nfig.show()","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:25:39.168716Z","iopub.execute_input":"2022-06-28T09:25:39.169115Z","iopub.status.idle":"2022-06-28T09:25:42.319598Z","shell.execute_reply.started":"2022-06-28T09:25:39.169083Z","shell.execute_reply":"2022-06-28T09:25:42.318516Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fig, ax = plt.subplots(1,3, figsize=(16,5))\nfig.suptitle('Relationships between Risk Variables,\\nLog-Transformed',fontsize=16)\nax[0].hexbin(x='Risk 8', y='Risk 5', data=plot_df, bins='log', gridsize=40, cmap='winter')\nax[0].text(5,35.7, 'Correlation: {:.2f}'.format(plot_df[['Risk 8','Risk 5']].corr().iloc[1,0]), \n           ha=\"center\", va=\"center\",bbox=dict(boxstyle=\"round,pad=0.3\",fc=\"white\"))\nax[0].set(xlabel='Risk 8',ylabel='Risk 5')\nax[1].hexbin(x='Risk 3', y='Risk 16', data=plot_df, bins='log', gridsize=40, cmap='winter')\nax[1].text(1.3,14.3, 'Correlation: {:.2f}'.format(plot_df[['Risk 3','Risk 16']].corr().iloc[1,0]), \n           ha=\"center\", va=\"center\",bbox=dict(boxstyle=\"round,pad=0.3\",fc=\"white\"))\nax[1].set(xlabel='Risk 3',ylabel='Risk 16')\nax[2].hexbin(x='Risk 20', y='Risk 17', data=plot_df, bins='log', gridsize=40, cmap='winter')\nax[2].text(7,1.02, 'Correlation: {:.2f}'.format(plot_df[['Risk 20','Risk 17']].corr().iloc[1,0]), \n           ha=\"center\", va=\"center\",bbox=dict(boxstyle=\"round,pad=0.3\",fc=\"white\"))\nax[2].set(xlabel='Risk 20',ylabel='Risk 17')\nfor i in range(3):\n    ax[i].tick_params(left=False,bottom=False)\nsns.despine()\nplt.tight_layout(rect=[0, 0, 1, 0.99])\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:25:49.060912Z","iopub.execute_input":"2022-06-28T09:25:49.061437Z","iopub.status.idle":"2022-06-28T09:25:50.436892Z","shell.execute_reply.started":"2022-06-28T09:25:49.061398Z","shell.execute_reply":"2022-06-28T09:25:50.435987Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"corr=train_df.corr()\ncorr=corr['Target'].sort_values(ascending=False)[1:-1]\npal=sns.color_palette(\"Reds_r\",135).as_hex()\nrgb=['rgba'+str(matplotlib.colors.to_rgba(i,0.7)) for i in pal]\nfig = go.Figure()\nfig.add_trace(go.Bar(x=corr[corr>=0], y=corr[corr>=0].index, \n                     marker_color=rgb, orientation='h', \n                     marker_line=dict(color=pal,width=2), name='',\n                     hovertemplate='%{y} correlation with target: %{x:.3f}',\n                     showlegend=False))\npal=sns.color_palette(\"Greens\",100).as_hex()\nrgb=['rgba'+str(matplotlib.colors.to_rgba(i,0.7)) for i in pal]\nfig.add_trace(go.Bar(x=corr[corr<0], y=corr[corr<0].index, \n                     marker_color=rgb[25:], orientation='h', \n                     marker_line=dict(color=pal[25:],width=2), name='',\n                     hovertemplate='%{y} correlation with target: %{x:.3f}',\n                     showlegend=False))\nfig.update_layout(template=temp,title=\"Feature Correlations with Target\",\n                  xaxis_title=\"Correlation\", margin=dict(l=150),\n                  height=3000, width=700, hovermode='closest')\nfig.show()","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:26:17.095875Z","iopub.execute_input":"2022-06-28T09:26:17.096296Z","iopub.status.idle":"2022-06-28T09:26:53.049240Z","shell.execute_reply.started":"2022-06-28T09:26:17.096260Z","shell.execute_reply":"2022-06-28T09:26:53.048238Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"***There are several strong correlations with the target variable. Payment 2 is the most negatively correlated with the probability of defaulting with a correlation of -0.67, while Delinquency 48 is the most positively correlated overall at 0.61. Delinquency 87 is also missing from the correlations above due to the proportion of null values. In fact, 24 of the top 30 features with missing values are in Delinquency variables.***","metadata":{}},{"cell_type":"code","source":"null=round((train_df.isna().sum()/train_df.shape[0]*100),2).sort_values(ascending=False).astype(str)+('%')\nnull=null.to_frame().rename(columns={0:'Missing %'})\nnull.head(30)","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:27:13.617304Z","iopub.execute_input":"2022-06-28T09:27:13.617732Z","iopub.status.idle":"2022-06-28T09:27:14.071822Z","shell.execute_reply.started":"2022-06-28T09:27:13.617697Z","shell.execute_reply":"2022-06-28T09:27:14.070863Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# **Building Model**","metadata":{}},{"cell_type":"code","source":"import warnings\nwarnings.filterwarnings('ignore')\n\ndf = pd.read_feather('../input/amexfeather/train_data.ftr')","metadata":{"id":"b14Hv9HklQKN","execution":{"iopub.status.busy":"2022-06-28T09:31:55.124789Z","iopub.execute_input":"2022-06-28T09:31:55.125226Z","iopub.status.idle":"2022-06-28T09:32:13.882149Z","shell.execute_reply.started":"2022-06-28T09:31:55.125188Z","shell.execute_reply":"2022-06-28T09:32:13.881364Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_cat = ['B_30', 'B_38', 'D_114', 'D_116', 'D_117', 'D_120', 'D_126','D_63','D_64', 'D_66', 'D_68'] \n\ndf_all = list(df.columns)\ndf_all.remove(\"customer_ID\")\ndf_all.remove(\"S_2\")\ndf_all.remove(\"D_142\")\n\n#finding set of numerical features by cosnducting simple set operations\ndf_num = list(set(df_all) - set(df_cat))\n\nprint(df_num[0:5])","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:32:20.105925Z","iopub.execute_input":"2022-06-28T09:32:20.106494Z","iopub.status.idle":"2022-06-28T09:32:20.115802Z","shell.execute_reply.started":"2022-06-28T09:32:20.106450Z","shell.execute_reply":"2022-06-28T09:32:20.114641Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df = df[df_all]\n\ndf.isnull().sum()","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:32:25.103750Z","iopub.execute_input":"2022-06-28T09:32:25.104232Z","iopub.status.idle":"2022-06-28T09:32:33.540631Z","shell.execute_reply.started":"2022-06-28T09:32:25.104195Z","shell.execute_reply":"2022-06-28T09:32:33.539854Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"perc = 20.0 # Like N %\nmin_count =  int(((100-perc)/100)*df.shape[0] + 1)\ndf = df.dropna( axis=1, \n                thresh=min_count)\ndf","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:32:39.498429Z","iopub.execute_input":"2022-06-28T09:32:39.499815Z","iopub.status.idle":"2022-06-28T09:32:48.889038Z","shell.execute_reply.started":"2022-06-28T09:32:39.499750Z","shell.execute_reply":"2022-06-28T09:32:48.887859Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"***Now, after removing certain features from the dataframe we clean it further by dropping all rows with NA, we have lost some data but still have a lot of data for model building nad testing.***","metadata":{}},{"cell_type":"code","source":"df=df.dropna()\ndf=df.reset_index()\ndf=df.drop(\"index\",axis=1)\n\ndf","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:32:56.787860Z","iopub.execute_input":"2022-06-28T09:32:56.788429Z","iopub.status.idle":"2022-06-28T09:33:09.099621Z","shell.execute_reply.started":"2022-06-28T09:32:56.788382Z","shell.execute_reply":"2022-06-28T09:33:09.098408Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_all = list(df.columns)\n\ndf_num = list(set(df_all) - set(df_cat))\n\ndf_cat = list(set(df_all) - set(df_num))\n\ndf_num[0:5]","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:33:18.001840Z","iopub.execute_input":"2022-06-28T09:33:18.002544Z","iopub.status.idle":"2022-06-28T09:33:18.010436Z","shell.execute_reply.started":"2022-06-28T09:33:18.002499Z","shell.execute_reply":"2022-06-28T09:33:18.009335Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_all=list(df.columns)\ndf_all.remove(\"target\")","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:33:23.414201Z","iopub.execute_input":"2022-06-28T09:33:23.415321Z","iopub.status.idle":"2022-06-28T09:33:23.419855Z","shell.execute_reply.started":"2022-06-28T09:33:23.415277Z","shell.execute_reply":"2022-06-28T09:33:23.418797Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_encoded = pd.get_dummies( df[df_all], \n                                        columns = df_cat,\n                                        drop_first = True )\n\ndf_encoded","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:33:33.372541Z","iopub.execute_input":"2022-06-28T09:33:33.373270Z","iopub.status.idle":"2022-06-28T09:33:38.536848Z","shell.execute_reply.started":"2022-06-28T09:33:33.373215Z","shell.execute_reply":"2022-06-28T09:33:38.535824Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X = df_encoded\nY = df['target']","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:33:44.276767Z","iopub.execute_input":"2022-06-28T09:33:44.277203Z","iopub.status.idle":"2022-06-28T09:33:44.283454Z","shell.execute_reply.started":"2022-06-28T09:33:44.277170Z","shell.execute_reply":"2022-06-28T09:33:44.281995Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\n\ntrain_X, test_X, train_y, test_y = train_test_split( X,\n                                                    Y,\n                                                    test_size = 0.3,\n                                                    random_state = 42 )","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:33:50.369034Z","iopub.execute_input":"2022-06-28T09:33:50.369482Z","iopub.status.idle":"2022-06-28T09:34:03.354090Z","shell.execute_reply.started":"2022-06-28T09:33:50.369447Z","shell.execute_reply":"2022-06-28T09:34:03.352857Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.preprocessing import StandardScaler\n\nsc = StandardScaler()\ntrain_X = sc.fit_transform(train_X)\ntest_X = sc.transform(test_X)","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:34:10.477951Z","iopub.execute_input":"2022-06-28T09:34:10.479474Z","iopub.status.idle":"2022-06-28T09:34:35.995094Z","shell.execute_reply.started":"2022-06-28T09:34:10.479391Z","shell.execute_reply":"2022-06-28T09:34:35.994226Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.linear_model import LogisticRegression\n\n\nlogit = LogisticRegression()\n\nlogit.fit( train_X, train_y)","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:34:45.417276Z","iopub.execute_input":"2022-06-28T09:34:45.417799Z","iopub.status.idle":"2022-06-28T09:35:59.741800Z","shell.execute_reply.started":"2022-06-28T09:34:45.417760Z","shell.execute_reply":"2022-06-28T09:35:59.740484Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pred_y = logit.predict(test_X)\n\nfrom sklearn.metrics import confusion_matrix, accuracy_score\ncm = confusion_matrix(test_y,pred_y)\nprint(cm)\naccuracy_score(test_y, pred_y)","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:36:11.812034Z","iopub.execute_input":"2022-06-28T09:36:11.813380Z","iopub.status.idle":"2022-06-28T09:36:14.493448Z","shell.execute_reply.started":"2022-06-28T09:36:11.813322Z","shell.execute_reply":"2022-06-28T09:36:14.492406Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn import metrics\nprint( metrics.classification_report( test_y, pred_y ) )","metadata":{"execution":{"iopub.status.busy":"2022-06-28T09:36:27.945870Z","iopub.execute_input":"2022-06-28T09:36:27.947171Z","iopub.status.idle":"2022-06-28T09:36:30.348350Z","shell.execute_reply.started":"2022-06-28T09:36:27.947109Z","shell.execute_reply":"2022-06-28T09:36:30.346996Z"},"trusted":true},"execution_count":null,"outputs":[]}]}