import pickle as pkl
import streamlit as st
from sklearn.linear_model import LinearRegression
import pandas as pd
from sklearn.model_selection import train_test_split

# loading the data
df = pd.read_csv('housing.csv')
df.rename(columns = {'Avg. Area Income':'Income','Avg. Area House Age':'House_age', 'Avg. Area Number of Rooms':'No_rooms',
       'Avg. Area Number of Bedrooms':'No_bedrooms', 'Area Population':'population'},inplace = True)

# we will drop number of bedrooms column from the dataset

df.drop(columns= ['No_bedrooms'],inplace=True)

X_train,X_test,y_train,y_test = train_test_split(df.drop(columns =['Price']),
                                                 df['Price'],
                                                 test_size = 0.2,
                                                 random_state =2)
#model building
from sklearn.linear_model import LinearRegression

lr = LinearRegression()
# training the model or fitting the model

lr.fit(X_train,y_train)

# FUNCTION
def user_report():
  Income = st.sidebar.slider('Income', 50000,107701, 58000 )
  House_age = st.sidebar.slider('House_age', 2,10, 4 )
  No_rooms = st.sidebar.slider('No_rooms', 3,11, 5 )
  population = st.sidebar.slider('population', 30000,70000, 50000 )
  

  user_report_data = {
      'Income':Income,
      'House_age':House_age,
      'No_rooms':No_rooms,
      'population':population
  }
  report_data = pd.DataFrame(user_report_data, index=[0])
  return report_data




# Housing Data
user_data = user_report()
st.subheader('Housing Data')
st.write(user_data)

# MODEL
user_result = lr.predict(user_data)



# VISUALISATIONS
st.title('Visualised Housing Data')



# COLOR FUNCTION
if user_result[0]==0:
  color = 'blue'
else:
  color = 'red'



# OUTPUT
st.subheader('Price of House is : ')
st.subheader(str(user_result[0]))