import gradio as gr

#Step 1
input1 = gr.inputs.Textbox(label="F1")
input2 = gr.inputs.Textbox(label="F2")
input3 = gr.inputs.Textbox(label="F3")
input4 = gr.inputs.Textbox(label="F4")
input5 = gr.inputs.Textbox(label="F5")
input6 = gr.inputs.Textbox(label="F6")
input7 = gr.inputs.Textbox(label="F7")
input8 = gr.inputs.Textbox(label="F8")

#output component
output1 = gr.outputs.Textbox(label = "Predicted housing prices")

#define a function to accept inputs and return outputs
def predict_house(input1, input2, input3, input4, input5, input6, input7, input8):
  #data processing
  import pandas as pd
  data = pd.read_csv("housing.csv")
  ## 1. split data to get train and test set
  from sklearn.model_selection import train_test_split
  train_set, test_set = train_test_split(data, 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


  ## 4. scale the numeric features in training set
  from sklearn.preprocessing import MinMaxScaler
  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)
  train_features_normalized

  #model training
  from sklearn.linear_model import LinearRegression ## import the LinearRegression Function
  lin_reg = LinearRegression() ## Initialize the class
  lin_reg.fit(train_features_normalized, train_labels) # feed the training data X, and label Y for supervised learning

  #model predictions
  

  import numpy as np

  test_feature = np.array([[input1, input2, input3, input4, input5, input6, input7, input8]])
  normalized_test_features = scaler.transform(test_feature)
  training_predictions = lin_reg.predict(normalized_test_features)




  return training_predictions


#Step 4: Build connection between front end and back end
gr.Interface(fn = predict_house,
             inputs = [input1, input2, input3, input4, input5, input6, input7, input8],
             outputs = [output1]).launch(debug = True)