# -*- coding: utf-8 -*-
"""Untitled0.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1fyFBMy_3a9yZumgON5rfSKvfibePbsRy
"""

# First, install Gradio
#!pip install --quiet gradio

import pandas as pd
housing = pd.read_csv("housing.csv")
import numpy as np
       
# split data to get train and test set
from sklearn.model_selection import train_test_split
train_set, test_set = train_test_split(housing, test_size=0.2, random_state=42)
#clean the missing values
train_set_clean = train_set.dropna(subset=["total_bedrooms"])
train_set_clean
train_labels = train_set_clean["median_house_value"].copy() 
train_features = train_set_clean.drop("median_house_value", axis=1) 

#scale the numeric features in training set
from sklearn.preprocessing import MinMaxScaler
scaler = MinMaxScaler() 
scaler.fit(train_features)

train_features_normalized = scaler.transform(train_features)
train_features_normalized

from sklearn.linear_model import LinearRegression 
lin_reg = LinearRegression() 
lin_reg.fit(train_features_normalized, train_labels)

def housing_price(longitude,latitude,housing_median_age,total_rooms,total_bedrooms,population,households,median_income):

    data = {'longitude':float(longitude),
            'latitude':float(latitude),
            'housing_median_age':float(housing_median_age),
            'total_rooms':float(total_rooms),
            'total_bedrooms':float(total_bedrooms),
            'population':float(population),
            'households':float(households),
            'median_income':float(median_income),
    }
    test_features = pd.DataFrame(columns=['longitude', 'latitude', 'housing_median_age', 'total_rooms',
                      'total_bedrooms', 'population', 'households', 'median_income'])
    
    test_features = test_features.append(data,ignore_index=True)
    test_features = test_features.dropna(subset=["total_bedrooms"])

    test_features_normalized = scaler.transform(test_features)
    test_features_normalized

    prediction = lin_reg.predict(test_features_normalized)[0]

    return prediction

import gradio as gr

input_module1 = gr.inputs.Slider(-124, -114, step=1, label = "Longitude")
input_module2 = gr.inputs.Slider(32, 41, step=1, label = "Latitude")
input_module3 = gr.inputs.Slider(1, 52, step=1, label = "Housing median age")
input_module4 = gr.inputs.Slider(2, 39329, step=10, label = "Total rooms")
input_module5 = gr.inputs.Slider(1, 6445, step=10, label = "Total bedrooms")
input_module6 = gr.inputs.Slider(3, 35682, step=10, label = "Population")
input_module7 = gr.inputs.Slider(1, 6082, step=10, label = "Households")
input_module8 = gr.inputs.Slider(0.5, 15, step=0.5, label = "Median Income")

output_module1 = gr.outputs.Textbox(label = "Predicted House Prices")

gr.Interface(fn = housing_price , inputs =[input_module1, input_module2, input_module3,
                     input_module4, input_module5, input_module6,
                     input_module7, input_module8], 
             outputs=[output_module1]
            ).launch()