{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":35332,"databundleVersionId":3723648,"sourceType":"competition"}],"dockerImageVersionId":31153,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\nimport seaborn as sns\nimport matplotlib.pyplot as plt\n\n# Load a sample of the training data\nusecols = ['customer_ID', 'S_2']\ntrain = pd.read_csv('/kaggle/input/amex-default-prediction/train_data.csv', usecols=usecols, nrows=200000)\nlabels = pd.read_csv('/kaggle/input/amex-default-prediction/train_labels.csv')\n\ntrain['S_2'] = pd.to_datetime(train['S_2'])\nlatest = train.sort_values(['customer_ID','S_2']).groupby('customer_ID').tail(1)\nmerged = latest.merge(labels, on='customer_ID', how='left')\n\n# Default rate by month\nmerged['month'] = merged['S_2'].dt.to_period('M').astype(str)\ntrend = merged.groupby('month')['target'].mean().reset_index()\n\n# Visualization\nplt.figure(figsize=(10,5))\nsns.lineplot(data=trend, x='month', y='target', marker='o', color='orange')\nplt.title('Average Default Rate Over Time')\nplt.xlabel('Month')\nplt.ylabel('Default Rate')\nplt.xticks(rotation=45)\nplt.tight_layout()\nplt.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-15T00:21:11.161434Z","iopub.execute_input":"2025-10-15T00:21:11.161660Z","iopub.status.idle":"2025-10-15T00:21:29.984869Z","shell.execute_reply.started":"2025-10-15T00:21:11.161640Z","shell.execute_reply":"2025-10-15T00:21:29.983774Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Load relevant columns\nusecols = ['customer_ID', 'S_2', 'P_2']  # P_2 = total payment amount\ntrain = pd.read_csv('/kaggle/input/amex-default-prediction/train_data.csv', usecols=usecols, nrows=200000)\nlabels = pd.read_csv('/kaggle/input/amex-default-prediction/train_labels.csv')\n\ntrain['S_2'] = pd.to_datetime(train['S_2'])\nlatest = train.sort_values(['customer_ID','S_2']).groupby('customer_ID').tail(1)\nmerged = latest.merge(labels, on='customer_ID', how='left')\n\n# Bucket payments\nmerged['payment_bucket'] = pd.qcut(merged['P_2'], q=5, labels=['Very Low','Low','Medium','High','Very High'])\n\n# Default rate by payment bucket\npayment_default = merged.groupby('payment_bucket')['target'].mean().reset_index()\n\n# Visualization\nplt.figure(figsize=(8,5))\nsns.barplot(data=payment_default, x='payment_bucket', y='target', palette='coolwarm')\nplt.title('Default Rate by Payment Amount Category')\nplt.xlabel('Payment Level')\nplt.ylabel('Default Rate')\nplt.tight_layout()\nplt.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-15T00:22:00.440711Z","iopub.execute_input":"2025-10-15T00:22:00.441076Z","iopub.status.idle":"2025-10-15T00:22:05.748799Z","shell.execute_reply.started":"2025-10-15T00:22:00.441048Z","shell.execute_reply":"2025-10-15T00:22:05.747815Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Load sample of spending and balance columns\nusecols = ['customer_ID', 'S_2', 'S_3', 'B_1']  # S_3=spend amount, B_1=balance\ntrain = pd.read_csv('/kaggle/input/amex-default-prediction/train_data.csv', usecols=usecols, nrows=200000)\nlabels = pd.read_csv('/kaggle/input/amex-default-prediction/train_labels.csv')\n\ntrain['S_2'] = pd.to_datetime(train['S_2'])\nlatest = train.sort_values(['customer_ID','S_2']).groupby('customer_ID').tail(1)\nmerged = latest.merge(labels, on='customer_ID', how='left')\n\n# Scatter plot: Spend vs Balance, colored by default\nplt.figure(figsize=(8,6))\nsns.scatterplot(data=merged.sample(5000), x='B_1', y='S_3', hue='target', palette='Set1', alpha=0.6)\nplt.title('Spend vs Balance — Colored by Default Status')\nplt.xlabel('Balance (B_1)')\nplt.ylabel('Spend (S_3)')\nplt.legend(title='Default', labels=['No Default','Default'])\nplt.tight_layout()\nplt.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-15T00:22:20.373886Z","iopub.execute_input":"2025-10-15T00:22:20.374264Z","iopub.status.idle":"2025-10-15T00:22:25.842712Z","shell.execute_reply.started":"2025-10-15T00:22:20.374238Z","shell.execute_reply":"2025-10-15T00:22:25.841106Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd, seaborn as sns, matplotlib.pyplot as plt\n\n# Load relevant columns\nusecols = ['customer_ID','S_2','D_39']\ntrain = pd.read_csv('/kaggle/input/amex-default-prediction/train_data.csv', usecols=usecols, nrows=200000)\nlabels = pd.read_csv('/kaggle/input/amex-default-prediction/train_labels.csv')\n\ntrain['S_2'] = pd.to_datetime(train['S_2'])\nlatest = train.sort_values(['customer_ID','S_2']).groupby('customer_ID').tail(1)\nmerged = latest.merge(labels, on='customer_ID', how='left')\n\n# Bucket delinquency score\nmerged['delinquency_bucket'] = pd.qcut(merged['D_39'], q=5, labels=['Very Low','Low','Medium','High','Very High'])\n\n# Default rate by delinquency bucket\ndelinq_rate = merged.groupby('delinquency_bucket')['target'].mean().reset_index()\n\nplt.figure(figsize=(8,5))\nsns.barplot(data=delinq_rate, x='delinquency_bucket', y='target', palette='rocket')\nplt.title('Default Rate by Delinquency Level (D_39)')\nplt.xlabel('Delinquency Level')\nplt.ylabel('Default Rate')\nplt.tight_layout()\nplt.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-15T00:26:27.354747Z","iopub.execute_input":"2025-10-15T00:26:27.355211Z","iopub.status.idle":"2025-10-15T00:26:32.463248Z","shell.execute_reply.started":"2025-10-15T00:26:27.355182Z","shell.execute_reply":"2025-10-15T00:26:32.461880Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"usecols = ['customer_ID','S_2','S_3']\ntrain = pd.read_csv('/kaggle/input/amex-default-prediction/train_data.csv', usecols=usecols, nrows=150000)\nlabels = pd.read_csv('/kaggle/input/amex-default-prediction/train_labels.csv')\n\ntrain['S_2'] = pd.to_datetime(train['S_2'])\nlatest = train.sort_values(['customer_ID','S_2']).groupby('customer_ID').tail(1)\nmerged = latest.merge(labels, on='customer_ID', how='left')\n\nplt.figure(figsize=(8,5))\nsns.kdeplot(data=merged, x='S_3', hue='target', fill=True, common_norm=False, palette='muted')\nplt.title('Spending Distribution (S_3) by Default Status')\nplt.xlabel('Spending Amount')\nplt.ylabel('Density')\nplt.tight_layout()\nplt.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-15T00:27:36.618867Z","iopub.execute_input":"2025-10-15T00:27:36.619272Z","iopub.status.idle":"2025-10-15T00:27:40.913339Z","shell.execute_reply.started":"2025-10-15T00:27:36.619243Z","shell.execute_reply":"2025-10-15T00:27:40.912128Z"}},"outputs":[],"execution_count":null}]}