Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| longitude = gr.inputs.Slider(-124.00, -114.00, step=0.01, label = "longitude") | |
| latitude = gr.inputs.Slider(32.00, 42.00, step=0.01, label = "latitude") | |
| housing_median_age = gr.inputs.Slider(1, 100, step=1, label = "housing_median_age") | |
| total_rooms = gr.inputs.Slider(1, 50000, step=1, label = "total_rooms") | |
| total_bedrooms = gr.inputs.Slider(1, 10000, step=1, label = "total_bedrooms") | |
| population = gr.inputs.Slider(1, 40000, step=1, label = "population") | |
| households = gr.inputs.Slider(1, 6100, step=1, label = "households") | |
| median_income = gr.inputs.Slider(0.1, 50, step=0.15, label = "median_income") | |
| pred_house_price = gr.outputs.Textbox(label = "predicting housing price") | |
| from sklearn.model_selection import train_test_split | |
| import pandas as pd | |
| ## 4. scale the numeric features in training set | |
| from sklearn.preprocessing import MinMaxScaler | |
| from sklearn.linear_model import LinearRegression | |
| import joblib | |
| import os | |
| def housing_predict(longitude, latitude, housing_median_age, total_rooms, total_bedrooms, population, | |
| households, median_income): | |
| """ | |
| [longitude, latitude, housing_median_age, total_rooms, total_bedrooms, population, | |
| households, median_income] | |
| """ | |
| item = [longitude, latitude, housing_median_age, total_rooms, total_bedrooms, population, | |
| households, median_income] | |
| print(f"passing parameters: {item}") | |
| if os.path.exists("sample_data/LinearRegressionHousing.pkl"): | |
| regr = joblib.load("sample_data/LinearRegressionHousing.pkl") | |
| print("load directly from pkl file") | |
| else: | |
| print("load training data...") | |
| housing = pd.read_csv('sample_data/housing.csv') | |
| train_set, test_set = train_test_split(housing, test_size=0.2, random_state=10) | |
| ## 2. clean the missing values | |
| train_set_clean = train_set.dropna(subset=["total_bedrooms"]) | |
| train_set_clean | |
| ## 2. derive training features and training labels | |
| train_labels = train_set_clean["median_house_value"].copy() # get labels for output label Y | |
| train_features = train_set_clean.drop("median_house_value", axis=1) # drop labels to get features X for training set | |
| scaler = MinMaxScaler() ## define the transformer | |
| scaler.fit(train_features) ## call .fit() method to calculate the min and max value for each column in dataset | |
| train_features_normalized = scaler.transform(train_features) | |
| lin_reg = LinearRegression() ## Initialize the class | |
| regr = lin_reg.fit(train_features_normalized, train_labels) # feed the training data X, and label Y for supervised learning | |
| if not os.path.exists("sample_data/LinearRegressionHousing.pkl"): | |
| joblib.dump(regr, "sample_data/LinearRegressionHousing.pkl") | |
| res = regr.predict([ item]) | |
| print(f"res={res}") | |
| return str(res[0]) | |
| gr.Interface(fn=housing_predict, inputs=[longitude, latitude, housing_median_age, total_rooms, total_bedrooms, population, | |
| households, median_income], outputs=pred_house_price).launch(debug=True) | |