# app.py import streamlit as st import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns from sklearn.linear_model import LinearRegression from sklearn.ensemble import RandomForestRegressor from sklearn.preprocessing import StandardScaler from sklearn.model_selection import train_test_split # Page configuration st.set_page_config(page_title="Data Analysis Platform", layout="wide") # Initialize session state if 'data' not in st.session_state: # Create sample data np.random.seed(42) dates = pd.date_range('2023-01-01', periods=100, freq='D') st.session_state.data = pd.DataFrame({ 'date': dates, 'sales': np.random.normal(1000, 200, 100), 'visitors': np.random.normal(500, 100, 100), 'conversion_rate': np.random.uniform(0.01, 0.05, 100), 'customer_satisfaction': np.random.normal(4.2, 0.5, 100), 'region': np.random.choice(['North', 'South', 'East', 'West'], 100) }) # Sidebar for navigation st.sidebar.title("Data Analytics Platform") page = st.sidebar.radio("Navigation", ["Home", "Data Explorer", "Visualization", "Predictions"]) # Home page if page == "Home": st.title("Data Analysis Platform") st.markdown(""" Welcome to the Data Analysis Platform. Explore your data with powerful visualizations and machine learning insights. """) col1, col2 = st.columns(2) with col1: st.subheader("Upload Your Dataset") uploaded_file = st.file_uploader("Choose a CSV file", type="csv") if uploaded_file is not None: try: st.session_state.data = pd.read_csv(uploaded_file) st.success("Data uploaded successfully!") except Exception as e: st.error(f"Error uploading file: {e}") with col2: st.subheader("Dataset Overview") st.write(st.session_state.data.describe()) # Data Explorer page elif page == "Data Explorer": st.title("Data Explorer") # Data summary st.subheader("Dataset Summary") st.write(f"Shape: {st.session_state.data.shape[0]} rows, {st.session_state.data.shape[1]} columns") # Show first few rows st.subheader("Data Preview") st.dataframe(st.session_state.data.head()) # Column analysis st.subheader("Column Analysis") col1, col2 = st.columns(2) with col1: column = st.selectbox("Select column to analyze:", st.session_state.data.columns) with col2: if pd.api.types.is_numeric_dtype(st.session_state.data[column]): analysis_type = st.selectbox( "Analysis type:", ["Distribution", "Time Series"] if "date" in column.lower() else ["Distribution"] ) else: analysis_type = st.selectbox("Analysis type:", ["Value Counts"]) # Display analysis if pd.api.types.is_numeric_dtype(st.session_state.data[column]): st.write(f"**Min:** {st.session_state.data[column].min():.2f}") st.write(f"**Max:** {st.session_state.data[column].max():.2f}") st.write(f"**Mean:** {st.session_state.data[column].mean():.2f}") st.write(f"**Median:** {st.session_state.data[column].median():.2f}") st.write(f"**Std Dev:** {st.session_state.data[column].std():.2f}") fig, ax = plt.subplots(figsize=(10, 6)) sns.histplot(st.session_state.data[column], ax=ax, kde=True) ax.set_title(f"Distribution of {column}") st.pyplot(fig) else: value_counts = st.session_state.data[column].value_counts() st.write(f"**Unique Values:** {len(value_counts)}") st.write(f"**Most Common:** {value_counts.index[0]} ({value_counts.iloc[0]} occurrences)") fig, ax = plt.subplots(figsize=(10, 6)) value_counts.plot(kind='bar', ax=ax) ax.set_title(f"Value counts for {column}") st.pyplot(fig) # Visualization page elif page == "Visualization": st.title("Data Visualization") chart_type = st.selectbox( "Select chart type:", ["Bar Chart", "Line Chart", "Scatter Plot", "Heatmap"] ) if chart_type in ["Bar Chart", "Line Chart"]: col1, col2 = st.columns(2) with col1: x_column = st.selectbox("X-axis:", st.session_state.data.columns) with col2: y_column = st.selectbox("Y-axis:", [col for col in st.session_state.data.columns if pd.api.types.is_numeric_dtype(st.session_state.data[col])]) # Aggregation for categorical x-axis if not pd.api.types.is_numeric_dtype(st.session_state.data[x_column]): agg_data = st.session_state.data.groupby(x_column)[y_column].mean().reset_index() fig, ax = plt.subplots(figsize=(10, 6)) if chart_type == "Bar Chart": sns.barplot(x=x_column, y=y_column, data=agg_data, ax=ax) else: # Line chart sns.lineplot(x=x_column, y=y_column, data=agg_data, ax=ax, marker='o') ax.set_title(f"{y_column} by {x_column}") st.pyplot(fig) else: fig, ax = plt.subplots(figsize=(10, 6)) if chart_type == "Bar Chart": sns.barplot(x=x_column, y=y_column, data=st.session_state.data, ax=ax) else: # Line chart sns.lineplot(x=x_column, y=y_column, data=st.session_state.data, ax=ax) ax.set_title(f"{y_column} vs {x_column}") st.pyplot(fig) elif chart_type == "Scatter Plot": col1, col2 = st.columns(2) with col1: x_column = st.selectbox("X-axis:", [col for col in st.session_state.data.columns if pd.api.types.is_numeric_dtype(st.session_state.data[col])]) with col2: y_column = st.selectbox("Y-axis:", [col for col in st.session_state.data.columns if pd.api.types.is_numeric_dtype(st.session_state.data[col]) and col != x_column]) fig, ax = plt.subplots(figsize=(10, 6)) sns.scatterplot(x=x_column, y=y_column, data=st.session_state.data, ax=ax) ax.set_title(f"{y_column} vs {x_column}") st.pyplot(fig) elif chart_type == "Heatmap": numeric_cols = st.session_state.data.select_dtypes(include=['number']).columns.tolist() correlation = st.session_state.data[numeric_cols].corr() fig, ax = plt.subplots(figsize=(10, 8)) sns.heatmap(correlation, annot=True, cmap='coolwarm', ax=ax) ax.set_title("Correlation Heatmap") st.pyplot(fig) # Predictions page elif page == "Predictions": st.title("ML Predictions") numeric_cols = st.session_state.data.select_dtypes(include=['number']).columns.tolist() st.subheader("Train a Model") col1, col2 = st.columns(2) with col1: target_column = st.selectbox("Target variable:", numeric_cols) with col2: model_type = st.selectbox("Model type:", ["Linear Regression", "Random Forest"]) # Select features feature_cols = [col for col in numeric_cols if col != target_column] selected_features = st.multiselect("Select features:", feature_cols, default=feature_cols) if st.button("Train Model"): if len(selected_features) > 0: # Prepare data X = st.session_state.data[selected_features] y = st.session_state.data[target_column] # Split data X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) # Scale features scaler = StandardScaler() X_train_scaled = scaler.fit_transform(X_train) X_test_scaled = scaler.transform(X_test) # Train model if model_type == "Linear Regression": model = LinearRegression() else: model = RandomForestRegressor(n_estimators=100, random_state=42) model.fit(X_train_scaled, y_train) # Evaluate train_score = model.score(X_train_scaled, y_train) test_score = model.score(X_test_scaled, y_test) st.session_state.model = model st.session_state.scaler = scaler st.session_state.features = selected_features st.success("Model trained successfully!") st.write(f"Training R² score: {train_score:.4f}") st.write(f"Testing R² score: {test_score:.4f}") # Feature importance for Random Forest if model_type == "Random Forest": importance = pd.DataFrame({ 'Feature': selected_features, 'Importance': model.feature_importances_ }).sort_values('Importance', ascending=False) fig, ax = plt.subplots(figsize=(10, 6)) sns.barplot(x='Importance', y='Feature', data=importance, ax=ax) ax.set_title("Feature Importance") st.pyplot(fig) else: st.error("Please select at least one feature") # Make predictions section st.subheader("Make Predictions") if 'model' in st.session_state: input_data = {} # Create input fields for each feature for feature in st.session_state.features: min_val = float(st.session_state.data[feature].min()) max_val = float(st.session_state.data[feature].max()) mean_val = float(st.session_state.data[feature].mean()) input_data[feature] = st.slider( f"Input {feature}:", min_value=min_val, max_value=max_val, value=mean_val ) if st.button("Predict"): # Prepare input for prediction input_df = pd.DataFrame([input_data]) input_scaled = st.session_state.scaler.transform(input_df) # Make prediction prediction = st.session_state.model.predict(input_scaled)[0] st.success(f"Predicted {target_column}: {prediction:.2f}") else: st.info("Train a model first to make predictions")