Create app.py

app.py

@@ -0,0 +1,91 @@
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LogisticRegression
+from sklearn.metrics import confusion_matrix, classification_report, accuracy_score, roc_auc_score
+from sklearn.preprocessing import StandardScaler
+import gradio as gr
+
+def credit_card_fraud_detection():
+    # Load the dataset
+    credit_card_data = pd.read_csv("creditcard.csv")
+
+    # Check for missing values
+    missing_values = credit_card_data.isnull().sum()
+
+    # Check class distribution
+    class_distribution = credit_card_data['Class'].value_counts()
+
+    # Visualize class distribution
+    sns.countplot(x='Class', data=credit_card_data)
+    plt.title('Class Distribution')
+    plt.show()
+
+    """This Dataset is highly unbalanced
+    0 --> Normal Transaction
+    1 --> fraudulent transaction
+    """
+
+    # separating the data for analysis
+    legit = credit_card_data[credit_card_data.Class == 0]
+    fraud = credit_card_data[credit_card_data.Class == 1]
+
+    # statistical measures of the data
+    legit_amount_stats = legit.Amount.describe()
+    fraud_amount_stats = fraud.Amount.describe()
+
+    # compare the values for both transactions
+    class_means = credit_card_data.groupby('Class').mean()
+
+    """Under-Sampling
+    Build a sample dataset containing a similar distribution of normal transactions and Fraudulent Transactions
+    Number of Fraudulent Transactions --> 492
+    """
+
+    legit_sample = legit.sample(n=492)
+
+    """Concatenating two DataFrames"""
+    new_dataset = pd.concat([legit_sample, fraud], axis=0)
+
+    class_value_counts = new_dataset['Class'].value_counts()
+
+    class_means_new_dataset = new_dataset.groupby('Class').mean()
+
+    """Splitting the data into Features & Targets"""
+    X = new_dataset.drop(columns='Class', axis=1)
+    Y = new_dataset['Class']
+
+    """Split the data into Training data & Testing Data"""
+    X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, stratify=Y, random_state=2)
+
+    """Model Training - Logistic Regression"""
+    model = LogisticRegression()
+
+    # training the Logistic Regression Model with Training Data
+    model.fit(X_train, Y_train)
+
+    """Model Evaluation - Accuracy Score"""
+    X_train_prediction = model.predict(X_train)
+    training_data_accuracy = accuracy_score(X_train_prediction, Y_train)
+
+    # accuracy on test data
+    X_test_prediction = model.predict(X_test)
+    test_data_accuracy = accuracy_score(X_test_prediction, Y_test)
+
+    return {
+        'missing_values': missing_values,
+        'class_distribution': class_distribution,
+        'legit_amount_stats': legit_amount_stats,
+        'fraud_amount_stats': fraud_amount_stats,
+        'class_means': class_means,
+        'class_value_counts': class_value_counts,
+        'class_means_new_dataset': class_means_new_dataset,
+        'training_data_accuracy': training_data_accuracy,
+        'test_data_accuracy': test_data_accuracy
+    }
+
+# Launching the Gradio Interface
+iface = gr.Interface(fn=credit_card_fraud_detection, title="Credit Card Fraud Detection")
+iface.launch()