| import streamlit as st | |
| import pandas as pd | |
| from sklearn.model_selection import train_test_split | |
| from sklearn.linear_model import LogisticRegression | |
| from sklearn.metrics import accuracy_score | |
| def run(): | |
| st.title("4. Modeling") | |
| st.write("## Overview") | |
| st.write("Building and training machine learning models to make predictions.") | |
| st.write("## Key Concepts & Explanations") | |
| st.markdown(""" | |
| - **Model Selection**: Choose the model based on the problem (e.g., Classification, Regression). | |
| - **Training Data**: The subset used to train the model. | |
| - **Test Data**: The subset used to evaluate the model’s performance. | |
| """) | |
| file = st.file_uploader("Upload a dataset for modeling", type=["csv"]) | |
| if file: | |
| df = pd.read_csv(file) | |
| target = st.selectbox("Select the target variable", df.columns) | |
| features = st.multiselect("Select the feature columns", df.columns) | |
| if target and features: | |
| X = df[features] | |
| y = df[target] | |
| X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) | |
| model = LogisticRegression() | |
| model.fit(X_train, y_train) | |
| y_pred = model.predict(X_test) | |
| accuracy = accuracy_score(y_test, y_pred) | |
| st.write(f"Accuracy: {accuracy * 100:.2f}%") | |
| st.write("## Quiz: Conceptual Questions") | |
| q1 = st.radio("What is overfitting?", ["Model too simple", "Model too complex", "Data too large"]) | |
| if q1 == "Model too complex": | |
| st.success("✅ Correct!") | |
| else: | |
| st.error("❌ Incorrect.") | |
| st.write("## Code-Based Quiz") | |
| code_input = st.text_area("Write a function to split data into train and test sets", value="def split_data(df, target):\n X = df.drop(columns=[target])\n y = df[target]\n return train_test_split(X, y, test_size=0.2, random_state=42)") | |
| if "train_test_split" in code_input: | |
| st.success("✅ Correct!") | |
| else: | |
| st.error("❌ Try again.") | |
| st.write("## Learning Resources") | |
| st.markdown(""" | |
| - 📖 [Introduction to Machine Learning with Python](https://www.oreilly.com/library/view/introduction-to-machine/9781449369880/) | |
| """) | |