Create app.py

app.py

@@ -0,0 +1,106 @@
+import pandas as pd
+import matplotlib.pyplot as plt
+%matplotlib inline
+churn=pd.read_csv(r"C:\Users\deepu\Downloads\archive (9)\churn-bigml-80.csv")
+churn
+import pandas as pd
+import seaborn as sns
+import matplotlib.pyplot as plt
+
+
+categorical_cols = churn.select_dtypes(include=['object']).columns.tolist()
+
+# One-hot encode categorical columns
+data_encoded = pd.get_dummies(churn, columns=categorical_cols, drop_first=True)
+
+# Calculate correlations with the target variable (assuming the target column is named 'churn')
+target = 'Churn'
+correlations = data_encoded.corr()[target].drop(target)  # Drop target's self-correlation
+
+# Sort correlations by absolute value (strongest to weakest correlation)
+correlations = correlations.sort_values(key=abs, ascending=False)
+
+# Plot the correlations as a bar chart
+plt.figure(figsize=(10, 8))
+sns.barplot(x=correlations.values, y=correlations.index, palette="coolwarm")
+plt.title("Feature Correlations with Churn")
+plt.xlabel("Correlation Coefficient")
+plt.ylabel("Features")
+plt.show()
+import pandas as pd
+
+
+# Identify categorical columns
+categorical_cols = churn.select_dtypes(include=['object']).columns.tolist()
+
+# One-hot encode categorical columns
+data_encoded = pd.get_dummies(churn, columns=categorical_cols, drop_first=True)
+
+# Calculate correlations with the target variable (assuming the target column is named 'churn')
+target = 'Churn'
+correlations = data_encoded.corr()[target].drop(target)  # Drop self-correlation of target
+
+# Filter features with correlation > 0.1 or < -0.05
+filtered_features = correlations[(correlations > 0.1) | (correlations < -0.05)].index.tolist()
+
+# Create a new DataFrame with only the filtered features and the target column
+data_filtered = data_encoded[filtered_features + [target]]
+
+# Save the filtered DataFrame to a CSV file
+data_filtered.to_csv("filtered_features_churn.csv", index=False)
+
+print("CSV file 'filtered_features_churn.csv' created successfully with filtered features.")
+data=pd.read_csv(r"filtered_features_churn.csv")
+data = data.drop(columns=["Churn"])
+import gradio as gr
+import numpy as np
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.model_selection import train_test_split
+
+X = data.drop(columns=["Churn"])
+y =data["Churn"]
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+model = RandomForestClassifier(random_state=42)
+model.fit(X_train, y_train)
+import gradio as gr
+import numpy as np
+from sklearn.preprocessing import StandardScaler
+from sklearn.ensemble import RandomForestClassifier
+
+
+# Initialize and fit the scaler
+scaler = StandardScaler()
+scaler.fit(X_train)  # Fit the scaler to your training data
+
+# Initialize and fit your model
+model = RandomForestClassifier()
+model.fit(X_train, y_train)  # Fit the model to your training data
+
+# Define a prediction function
+def predict_churn(*features):
+    input_data = np.array(features).reshape(1, -1)
+    input_data_scaled = scaler.transform(input_data)  # Use the fitted scaler here
+    
+    # Predict churn probability
+    prediction = model.predict(input_data_scaled)
+    return "Churn" if prediction[0] == 1 else "Not Churn"
+
+# Example feature labels (adjust based on your dataset)
+feature_labels = ['Number vmail messages', 'Total day minutes', 'Total day charge',
+       'Total intl calls', 'Customer service calls', 'International plan_Yes',
+       'Voice mail plan_Yes']  # Replace with your actual feature names
+
+# Set up Gradio interface
+interface = gr.Interface(
+    fn=predict_churn,
+    inputs=[gr.Number(label=label) for label in feature_labels],
+    outputs="text",
+    title="Customer Churn Prediction",
+    description="Enter customer information to predict churn .",
+    theme="soft",
+    flagging_options=["average prediction", "good prediction", "bad prediction"]
+
+)
+
+# Launch the interface
+interface.launch(share=True)