Risk Prediction System with PDF generation

risk_predection_system/dataExploration.py

@@ -0,0 +1,13 @@
+import pandas as pd
+import seaborn as sns
+import matplotlib.pyplot as plt
+
+data = pd.read_csv('german_credit_data.csv')
+
+print(data.head())
+print(data.info())
+print(data.isnull().sum())
+
+sns.countplot(x='Risk', data=data)
+plt.title('Distribution of Risk')
+plt.show()

risk_predection_system/featureEngineering.py

@@ -0,0 +1,14 @@
+from sklearn.preprocessing import LabelEncoder, StandardScaler
+import pandas as pd
+
+data = pd.read_csv('german_credit_data.csv')
+
+label_encoders = {}
+for column in data.select_dtypes(include=['object']).columns:
+    label_encoders[column] = LabelEncoder()
+    data[column] = label_encoders[column].fit_transform(data[column])
+
+scaler = StandardScaler()
+numerical_features = data.select_dtypes(include=['int64', 'float64']).columns
+data[numerical_features] = scaler.fit_transform(data[numerical_features])
+print(data.head())