Download src/streamlit_app.py from ogayakwad9/Manisha_G_Project_Model_Deployment: direct link, hf CLI and curl.
- Browser
- Download file 3.34 kB
-
https://huggingface.co/spaces/ogayakwad9/Manisha_G_Project_Model_Deployment/resolve/main/src/streamlit_app.py
- Command line
-
hf download hf://spaces/ogayakwad9/Manisha_G_Project_Model_Deployment/src/streamlit_app.py
-
curl -L -o streamlit_app.py https://huggingface.co/spaces/ogayakwad9/Manisha_G_Project_Model_Deployment/resolve/main/src/streamlit_app.py
3.34 kB
| import streamlit as st | |
| import pandas as pd | |
| import numpy as np | |
| import joblib | |
| import matplotlib.pyplot as plt | |
| import seaborn as sns | |
| from sklearn.model_selection import train_test_split | |
| from sklearn.pipeline import Pipeline | |
| from sklearn.compose import ColumnTransformer | |
| from sklearn.preprocessing import OneHotEncoder, StandardScaler | |
| from sklearn.ensemble import RandomForestClassifier | |
| from sklearn.metrics import accuracy_score, confusion_matrix | |
| st.set_page_config(page_title="Lead Conversion Predictor", layout="wide") | |
| st.title("π ExtraaLearn Lead Conversion Predictor") | |
| # Upload dataset | |
| uploaded_file = st.file_uploader("Upload CSV Dataset", type=["csv"]) | |
| if uploaded_file: | |
| data = pd.read_csv(uploaded_file) | |
| st.subheader("Dataset Preview") | |
| st.dataframe(data.head()) | |
| # Drop ID if exists | |
| if "ID" in data.columns: | |
| data = data.drop("ID", axis=1) | |
| # Target | |
| target = "status" | |
| # Split features | |
| X = data.drop(target, axis=1) | |
| y = data[target] | |
| # Identify columns | |
| cat_cols = X.select_dtypes(include="object").columns.tolist() | |
| num_cols = X.select_dtypes(exclude="object").columns.tolist() | |
| # Preprocessing | |
| preprocessor = ColumnTransformer([ | |
| ("num", StandardScaler(), num_cols), | |
| ("cat", OneHotEncoder(handle_unknown="ignore"), cat_cols) | |
| ]) | |
| # Model | |
| model = Pipeline([ | |
| ("preprocessor", preprocessor), | |
| ("classifier", RandomForestClassifier(random_state=42)) | |
| ]) | |
| # Train-test split | |
| X_train, X_test, y_train, y_test = train_test_split( | |
| X, y, test_size=0.2, random_state=42 | |
| ) | |
| model.fit(X_train, y_train) | |
| preds = model.predict(X_test) | |
| acc = accuracy_score(y_test, preds) | |
| st.success(f"Model Accuracy: {acc:.2f}") | |
| # Confusion Matrix | |
| st.subheader("Confusion Matrix") | |
| cm = confusion_matrix(y_test, preds) | |
| fig, ax = plt.subplots() | |
| sns.heatmap(cm, annot=True, fmt="d", ax=ax) | |
| st.pyplot(fig) | |
| # --------------------------- | |
| # EDA SECTION | |
| # --------------------------- | |
| st.subheader("π Exploratory Data Analysis") | |
| col1, col2 = st.columns(2) | |
| with col1: | |
| st.write("### Age Distribution") | |
| fig, ax = plt.subplots() | |
| sns.histplot(data["age"], kde=True, ax=ax) | |
| st.pyplot(fig) | |
| with col2: | |
| st.write("### Website Visits") | |
| fig, ax = plt.subplots() | |
| sns.histplot(data["website_visits"], kde=True, ax=ax) | |
| st.pyplot(fig) | |
| st.write("### Conversion by Occupation") | |
| fig, ax = plt.subplots() | |
| sns.countplot(data=data, x="current_occupation", hue="status", ax=ax) | |
| st.pyplot(fig) | |
| # --------------------------- | |
| # PREDICTION UI | |
| # --------------------------- | |
| st.subheader("π― Predict New Lead") | |
| input_data = {} | |
| for col in X.columns: | |
| if col in cat_cols: | |
| input_data[col] = st.selectbox(col, data[col].unique()) | |
| else: | |
| input_data[col] = st.number_input(col, float(data[col].min()), float(data[col].max())) | |
| if st.button("Predict"): | |
| input_df = pd.DataFrame([input_data]) | |
| prediction = model.predict(input_df)[0] | |
| prob = model.predict_proba(input_df)[0][1] | |
| st.success(f"Prediction: {'Converted' if prediction == 1 else 'Not Converted'}") | |
| st.info(f"Conversion Probability: {prob:.2f}") | |