app.py

import gradio as gr
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.ensemble import RandomForestClassifier
from sklearn.preprocessing import LabelEncoder
from sklearn.impute import SimpleImputer
from io import BytesIO
import warnings

warnings.filterwarnings("ignore")

def read_file(file):
    try:
        if file.name.endswith(".csv"):
            df = pd.read_csv(file)
        elif file.name.endswith(".xlsx"):
            df = pd.read_excel(file)
        else:
            raise ValueError("Unsupported file format. Please upload a CSV or Excel file.")

        # Ensure the file has columns
        if df.empty or df.columns.size == 0:
            raise ValueError("The file has no data or valid columns to parse.")

        return df
    except Exception as e:
        raise ValueError(f"Error reading file: {str(e)}")

# Clean the data
def clean_data(df):
    # Drop duplicates
    df = df.drop_duplicates()
    # Fill missing values
    imputer = SimpleImputer(strategy="most_frequent")
    df = pd.DataFrame(imputer.fit_transform(df), columns=df.columns)
    return df

# Generate summary statistics
def generate_summary(df):
    return df.describe(include="all").transpose()

# Correlation heatmap
def generate_correlation_heatmap(df):
    numeric_df = df.select_dtypes(include=[np.number])
    corr = numeric_df.corr()
    plt.figure(figsize=(10, 8))
    sns.heatmap(corr, annot=True, cmap="coolwarm", fmt=".2f")
    buf = BytesIO()
    plt.savefig(buf, format="png")
    buf.seek(0)
    plt.close()
    return buf

# Feature importance using Random Forest
def feature_importance(df):
    # Encode categorical variables
    df_encoded = df.copy()
    label_encoders = {}
    for col in df_encoded.select_dtypes(include="object").columns:
        le = LabelEncoder()
        df_encoded[col] = le.fit_transform(df_encoded[col])
        label_encoders[col] = le

    # Target variable selection
    target_column = df_encoded.columns[-1]
    X = df_encoded.iloc[:, :-1]
    y = df_encoded[target_column]

    # Fit Random Forest
    model = RandomForestClassifier(random_state=42)
    model.fit(X, y)

    # Get feature importance
    importance = pd.DataFrame({
        "Feature": X.columns,
        "Importance": model.feature_importances_
    }).sort_values(by="Importance", ascending=False)

    return importance

# Visualize feature importance
def plot_feature_importance(importance):
    plt.figure(figsize=(10, 6))
    sns.barplot(x="Importance", y="Feature", data=importance)
    plt.title("Feature Importance")
    buf = BytesIO()
    plt.savefig(buf, format="png")
    buf.seek(0)
    plt.close()
    return buf

def analyze_file(file):
    try:
        # Step 1: Read file
        df = read_file(file)

        # Check if the dataframe is empty
        if df.empty:
            return (
                "The uploaded file is empty or has no valid data.",
                None,
                None,
                None,
            )

        # Step 2: Clean data
        df_cleaned = clean_data(df)

        # Check if the cleaned dataframe is still empty
        if df_cleaned.empty:
            return (
                "The dataset contains no valid data after cleaning.",
                None,
                None,
                None,
            )

        # Step 3: Generate summary statistics
        summary = generate_summary(df_cleaned)

        # Step 4: Generate correlation heatmap
        heatmap_buf = generate_correlation_heatmap(df_cleaned)

        # Step 5: Feature importance analysis
        importance = feature_importance(df_cleaned)
        importance_plot_buf = plot_feature_importance(importance)

        # Step 6: Return results
        return (
            summary,
            heatmap_buf,
            importance.head(10),  # Top 10 important features
            importance_plot_buf,
        )
    except ValueError as ve:
        # Handle file format issues or parsing errors
        return (
            f"ValueError: {str(ve)}",
            None,
            None,
            None,
        )
    except Exception as e:
        # Catch any other unforeseen issues
        return (
            f"An unexpected error occurred: {str(e)}",
            None,
            None,
            None,
        )

# Gradio Interface
def gradio_interface():
    with gr.Blocks() as interface:
        gr.Markdown("# AI Data Analytics Tool")
        gr.Markdown("Upload your dataset in CSV or Excel format to analyze and generate insights automatically.")

        with gr.Row():
            file_input = gr.File(label="Upload your CSV or Excel file")
            analyze_button = gr.Button("Analyze")

        with gr.Row():
            summary_output = gr.Dataframe(label="Summary Statistics")
            heatmap_output = gr.Image(label="Correlation Heatmap")
            importance_output = gr.Dataframe(label="Feature Importance")
            importance_plot_output = gr.Image(label="Feature Importance Plot")

        analyze_button.click(
            analyze_file,
            inputs=file_input,
            outputs=[summary_output, heatmap_output, importance_output, importance_plot_output],
        )

    return interface

interface = gradio_interface()
interface.launch(debug=True)