import gradio as gr import joblib import pandas as pd import numpy as np from sklearn.preprocessing import LabelEncoder, StandardScaler, OneHotEncoder from sklearn.impute import KNNImputer from sklearn.decomposition import PCA import pickle from tensorflow.keras.models import load_model import pickle import hdbscan def predict_ann(age, workclass, education, occupation, race, gender, capital_gain, capital_loss, hours_per_week, native_country): columns = { "0":[0], "age": [age], "workclass":[workclass], "educational-num":[education], "occupation":[occupation], "race":[race], "gender":[gender], "capital-gain":[capital_gain], "capital-loss":[capital_loss], "hours-per-week":[hours_per_week], "native-country":[native_country]} df = pd.DataFrame(data=columns) fixed_features = cleaning_features(df,race,False) print(fixed_features) ann_model = load_model('ann_model.h5') prediction = ann_model.predict(fixed_features) return "Income >50K" if prediction == 1 else "Income <=50K" def predict_rf(age, workclass, education, occupation, race, gender, capital_gain, capital_loss, hours_per_week, native_country): columns = { "age": [age], "workclass":[workclass], "educational-num":[education], "occupation":[occupation], "race":[race], "gender":[gender], "capital-gain":[capital_gain], "capital-loss":[capital_loss], "hours-per-week":[hours_per_week], "native-country":[native_country]} df = pd.DataFrame(data=columns) fixed_features = cleaning_features(df,race,False) print(fixed_features) rf_model = pickle.load(open('rf_model.pkl', 'rb')) return "Income >50K" if prediction == 1 else "Income <=50K" def predict_hb(age, workclass, education, occupation, race, gender, capital_gain, capital_loss, hours_per_week, native_country): columns = { "age": [age], "workclass":[workclass], "educational-num":[education], "occupation":[occupation], "race":[race], "gender":[gender], "capital-gain":[capital_gain], "capital-loss":[capital_loss], "hours-per-week":[hours_per_week], "native-country":[native_country]} df = pd.DataFrame(data=columns) fixed_features = cleaning_features(df,race,True) print(fixed_features) # hdb_model = pickle.load(open('hdbscan_model.pkl', 'rb')) # prediction = hdb_model.approximate_predict(fixed_features) scaler = StandardScaler() X = scaler.fit_transform(fixed_features) clusterer = hdbscan.HDBSCAN( min_cluster_size=220, min_samples=117, metric='euclidean', cluster_selection_method='eom', prediction_data=True, cluster_selection_epsilon=0.28479667859306007 ) prediction = clusterer.fit_predict(X) filename = 'hdbscan_model.pkl' pickle.dump(clusterer, open(filename, 'wb')) return f"Predicted Cluster (HDBSCAN): {prediction[-1]}" def cleaning_features(data,race,hdbscan): # with open('race_onehot_encoder.pkl', 'rb') as enc_file: # encoder = pickle.load(enc_file) with open('label_encoder_work.pkl', 'rb') as le_file: le_work = pickle.load(le_file) with open('label_encoder_occ.pkl', 'rb') as le_file: le_occ = pickle.load(le_file) with open('scaler.pkl', 'rb') as scaler_file: scaler = pickle.load(scaler_file) education_num_mapping = { "Preschool": 1, "1st-4th": 2, "5th-6th": 3, "7th-8th": 4, "9th": 5, "10th": 6, "11th": 7, "12th": 8, "HS-grad": 9, "Some-college": 10, "Assoc-voc": 11, "Assoc-acdm": 12, "Bachelors": 13, "Masters": 14, "Doctorate": 15, "Prof-school": 16 } race_categories = ["Amer-Indian-Eskimo", "Asian-Pac-Islander","Black", "Other","White"] gender_mapping = {"Male":1,"Female":0} country_mapping = {"United-States":1,"Other":0} numeric_cols = ['age', 'educational-num', 'hours-per-week'] # columns_to_encode = ['race','marital-status','relationship'] columns_to_encode = ['race'] data['workclass'] = le_work.transform(data['workclass']) data['occupation'] = le_occ.transform(data['occupation']) data['gender'] = data['gender'].map(gender_mapping) data['native-country'] = data['native-country'].map(country_mapping) data['educational-num'] = data['educational-num'].map(education_num_mapping) data[numeric_cols] = scaler.transform(data[numeric_cols]) for races in race_categories: if race == races: data[f'race_{races}'] = 1 else: data[f'race_{races}'] = 0 data = data.drop(columns=['race']) data = pca(data) if(hdbscan): df_transformed = pd.read_csv('dataset.csv') X = df_transformed.drop('income', axis=1) data = pd.concat([X, data], ignore_index=True) data['capital-gain'] = np.log1p(data['capital-gain']) data['capital-loss'] = np.log1p(data['capital-loss']) scaler = joblib.load("robust_scaler.pkl") numerical_features = ['age', 'capital-gain', 'capital-loss', 'hours-per-week'] data[numerical_features] = scaler.transform(data[numerical_features]) return data def pca(data): encoder_pkl = 'onehot_encoder.pkl' pca_model_pkl = 'pca.pkl' with open(pca_model_pkl, 'rb') as file: pca_model = pickle.load(file) with open(encoder_pkl, 'rb') as file: encoder = pickle.load(file) one_hot_encoded = encoder.transform(data[['workclass', 'occupation']]) encoded_columns_df = pd.DataFrame(one_hot_encoded, columns=encoder.get_feature_names_out()) pca_result_net = pca_model.transform(encoded_columns_df) pca_columns = [f'pca_component_{i+1}' for i in range(pca_model.n_components_)] pca_df = pd.DataFrame(pca_result_net, columns=pca_columns) data = data.drop(columns=['workclass', 'occupation'], axis=1) data = pd.concat([data, pca_df], axis=1) return data def hbdscan_tranform(df_transformed): df_transformed['capital-gain'] = np.log1p(df_transformed['capital-gain']) df_transformed['capital-loss'] = np.log1p(df_transformed['capital-loss']) # Apply RobustScaler to all numerical features numerical_features = ['age', 'capital-gain', 'capital-loss', 'hours-per-week'] scaler = RobustScaler() df_transformed[numerical_features] = scaler.fit_transform(df_transformed[numerical_features]) return df_transformed # Shared inputs ann_inputs = [ gr.Slider(18, 90, step=1, label="Age"), gr.Dropdown( ["Private", "Self-emp-not-inc", "Self-emp-inc", "Federal-gov", "Local-gov", "State-gov", "Without-pay", "Never-worked"], label="Workclass" ), gr.Dropdown( ["Bachelors", "Some-college", "11th", "HS-grad", "Prof-school", "Assoc-acdm", "Assoc-voc", "9th", "7th-8th", "12th", "Masters", "1st-4th", "10th", "Doctorate", "5th-6th", "Preschool"], label="Education" ), gr.Dropdown( ["Tech-support", "Craft-repair", "Other-service", "Sales", "Exec-managerial", "Prof-specialty", "Handlers-cleaners", "Machine-op-inspct", "Adm-clerical", "Farming-fishing", "Transport-moving", "Priv-house-serv", "Protective-serv", "Armed-Forces"], label="Occupation" ), gr.Dropdown( ["White", "Black", "Asian-Pac-Islander", "Amer-Indian-Eskimo", "Other"], label="Race" ), gr.Dropdown( ["Male", "Female"], label="Gender" ), gr.Slider(1, 60, step=1, label="Hours Per Week"), gr.Slider(0, 100000, step=100, label="Capital Gain"), gr.Slider(0, 5000, step=50, label="Capital Loss"), gr.Dropdown( ["United-States", "Other"], label="Native Country" ) ] rf_inputs = [ gr.Slider(18, 90, step=1, label="Age"), gr.Dropdown( ["Private", "Self-emp-not-inc", "Self-emp-inc", "Federal-gov", "Local-gov", "State-gov", "Without-pay", "Never-worked"], label="Workclass" ), gr.Dropdown( ["Bachelors", "Some-college", "11th", "HS-grad", "Prof-school", "Assoc-acdm", "Assoc-voc", "9th", "7th-8th", "12th", "Masters", "1st-4th", "10th", "Doctorate", "5th-6th", "Preschool"], label="Education" ), gr.Dropdown( ["Tech-support", "Craft-repair", "Other-service", "Sales", "Exec-managerial", "Prof-specialty", "Handlers-cleaners", "Machine-op-inspct", "Adm-clerical", "Farming-fishing", "Transport-moving", "Priv-house-serv", "Protective-serv", "Armed-Forces"], label="Occupation" ), gr.Dropdown( ["White", "Black", "Asian-Pac-Islander", "Amer-Indian-Eskimo", "Other"], label="Race" ), gr.Dropdown( ["Male", "Female"], label="Gender" ), gr.Slider(1, 60, step=1, label="Hours Per Week"), gr.Slider(0, 100000, step=100, label="Capital Gain"), gr.Slider(0, 5000, step=50, label="Capital Loss"), gr.Dropdown( ["United-States", "Other"], label="Native Country" ) ] hbd_inputs = [ gr.Slider(18, 90, step=1, label="Age"), gr.Dropdown( ["Private", "Self-emp-not-inc", "Self-emp-inc", "Federal-gov", "Local-gov", "State-gov", "Without-pay", "Never-worked"], label="Workclass" ), gr.Dropdown( ["Bachelors", "Some-college", "11th", "HS-grad", "Prof-school", "Assoc-acdm", "Assoc-voc", "9th", "7th-8th", "12th", "Masters", "1st-4th", "10th", "Doctorate", "5th-6th", "Preschool"], label="Education" ), gr.Dropdown( ["Tech-support", "Craft-repair", "Other-service", "Sales", "Exec-managerial", "Prof-specialty", "Handlers-cleaners", "Machine-op-inspct", "Adm-clerical", "Farming-fishing", "Transport-moving", "Priv-house-serv", "Protective-serv", "Armed-Forces"], label="Occupation" ), gr.Dropdown( ["White", "Black", "Asian-Pac-Islander", "Amer-Indian-Eskimo", "Other"], label="Race" ), gr.Dropdown( ["Male", "Female"], label="Gender" ), gr.Slider(1, 60, step=1, label="Hours Per Week"), gr.Slider(0, 100000, step=100, label="Capital Gain"), gr.Slider(0, 5000, step=50, label="Capital Loss"), gr.Dropdown( ["United-States", "Other"], label="Native Country" ) ] # Interfaces for each model ann_interface = gr.Interface( fn=predict_ann, inputs=ann_inputs, outputs="text", title="Artificial Neural Network", description="Predict income using an Artificial Neural Network." ) rf_interface = gr.Interface( fn=predict_rf, inputs=rf_inputs, outputs="text", title="Random Forest", description="Predict income using a Random Forest model." ) hb_interface = gr.Interface( fn=predict_hb, inputs=hbd_inputs, outputs="text", title="HDBScan Clustering", description="Predict income using a HDBScan Clustering model." ) interface = gr.TabbedInterface( [ann_interface, rf_interface, hb_interface], ["ANN Model", "Random Forest Model", "HDBScan Model"] ) interface.launch()