Create 5_model training /deployment

pages/5_model training /deployment

@@ -0,0 +1,132 @@
+import streamlit as st
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+from sklearn.linear_model import LinearRegression, LogisticRegression
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.metrics import accuracy_score, classification_report, mean_squared_error
+
+st.set_page_config(page_title="Zero to Hero - ML Model Trainer", layout="wide")
+st.title("📊 Machine Learning: Model Building, Training, and Deployment")
+
+# Sidebar Navigation
+st.sidebar.title("Navigation")
+section = st.sidebar.selectbox("Choose Step", [
+    "Upload Dataset",
+    "Model Selection",
+    "Model Training",
+    "Model Evaluation",
+    "Model Deployment"
+])
+
+# Session state
+if 'df' not in st.session_state:
+    st.session_state.df = None
+if 'model' not in st.session_state:
+    st.session_state.model = None
+
+# Upload dataset
+if section == "Upload Dataset":
+    st.header("📁 Upload Your Dataset")
+    uploaded_file = st.file_uploader("Upload CSV File", type=["csv"])
+    if uploaded_file:
+        df = pd.read_csv(uploaded_file)
+        st.session_state.df = df
+        st.dataframe(df.head())
+
+# Model selection
+elif section == "Model Selection":
+    st.header("🧠 Choose Your ML Algorithm")
+    if st.session_state.df is not None:
+        df = st.session_state.df
+        st.write("Select the target column (what you want to predict):")
+        target = st.selectbox("Target", df.columns)
+        features = df.drop(columns=[target])
+        X = features
+        y = df[target]
+
+        task_type = st.radio("What type of problem is it?", ["Regression", "Classification"])
+
+        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+        scaler = StandardScaler()
+        X_train = scaler.fit_transform(X_train)
+        X_test = scaler.transform(X_test)
+
+        if task_type == "Regression":
+            model_option = st.selectbox("Select Algorithm", ["Linear Regression"])
+            if model_option == "Linear Regression":
+                model = LinearRegression()
+
+        else:
+            model_option = st.selectbox("Select Algorithm", [
+                "Logistic Regression",
+                "K-Nearest Neighbors",
+                "Decision Tree",
+                "Random Forest"
+            ])
+
+            if model_option == "Logistic Regression":
+                model = LogisticRegression()
+            elif model_option == "K-Nearest Neighbors":
+                model = KNeighborsClassifier()
+            elif model_option == "Decision Tree":
+                model = DecisionTreeClassifier()
+            elif model_option == "Random Forest":
+                model = RandomForestClassifier()
+
+        st.session_state.model = model
+        st.session_state.X_train = X_train
+        st.session_state.X_test = X_test
+        st.session_state.y_train = y_train
+        st.session_state.y_test = y_test
+        st.success(f"{model_option} selected and data split for training/testing.")
+
+    else:
+        st.warning("Please upload a dataset first.")
+
+# Model training
+elif section == "Model Training":
+    st.header("🏋️ Model Training")
+    if st.session_state.model is not None:
+        model = st.session_state.model
+        model.fit(st.session_state.X_train, st.session_state.y_train)
+        st.session_state.trained_model = model
+        st.success("Model trained successfully!")
+    else:
+        st.warning("Please select a model first.")
+
+# Evaluation
+elif section == "Model Evaluation":
+    st.header("📈 Model Evaluation")
+    if 'trained_model' in st.session_state:
+        model = st.session_state.trained_model
+        y_pred = model.predict(st.session_state.X_test)
+        if isinstance(model, LinearRegression):
+            mse = mean_squared_error(st.session_state.y_test, y_pred)
+            st.write(f"Mean Squared Error: {mse:.4f}")
+        else:
+            acc = accuracy_score(st.session_state.y_test, y_pred)
+            st.write(f"Accuracy: {acc*100:.2f}%")
+            st.text("Classification Report:")
+            st.text(classification_report(st.session_state.y_test, y_pred))
+    else:
+        st.warning("Train a model first.")
+
+# Deployment
+elif section == "Model Deployment":
+    st.header("🚀 Deployment & Inference")
+    if 'trained_model' in st.session_state:
+        st.write("Upload a new CSV file with same features to test the model on new data:")
+        new_file = st.file_uploader("Upload New Data", type=["csv"], key="new_data")
+        if new_file:
+            new_df = pd.read_csv(new_file)
+            st.write("New Input Data:")
+            st.dataframe(new_df.head())
+            scaled_input = StandardScaler().fit_transform(new_df)
+            predictions = st.session_state.trained_model.predict(scaled_input)
+            st.write("Predictions:")
+            st.write(predictions)
+    else:
+        st.warning("Please train and evaluate a model before deploying.")