preprocess.py

# Abhishek
# Razorpod
# Loading Dataset for training and calling dataframes
import pandas as pd
from sklearn.preprocessing import LabelEncoder

# Load dataset
df = pd.read_csv("ad_ctr_sample_data.csv")

# Encode categorical variables
encoder = LabelEncoder()
df["Ad Copy"] = encoder.fit_transform(df["Ad Copy"])
df["Image Type"] = encoder.fit_transform(df["Image Type"])
df["CTA"] = encoder.fit_transform(df["CTA"])
df["Target Audience"] = encoder.fit_transform(df["Target Audience"])

# Feature engineering
df["Engagement Score"] = df["Clicks"] / df["Impressions"]

# Save processed data
df.to_csv("processed_ad_data.csv", index=False)
print("Data preprocessed and saved!")