import gradio as gr

input_module1 = gr.inputs.Slider(-124.35, -114.35, step=5, label = "Longitude")

input_module2 = gr.inputs.Slider(32, 41, step=5, label = "Latitude")

input_module3 = gr.inputs.Slider(1, 52, step=5, label = "Housing_median_age (Year)")

input_module4 = gr.inputs.Slider(1, 39996, step=5, label = "Total_rooms")

input_module5 = gr.inputs.Slider(1, 6441, step=5, label = "Total_bedrooms")

input_module6 = gr.inputs.Slider(3, 35678, step=5, label = "Population")

input_module7 = gr.inputs.Slider(1, 6081, step=5, label = "Households")

input_module8 = gr.inputs.Slider(0, 15, step=5, label = "Median_income")

examples = [["Longitude[-118,-123,-154,-129,-121]"], ["Latitude[32,23,12,16,17]"],["Housing_median_age (Year)[32,23,1,16,49]"], ["Total_rooms[32,23,1,16,49]"],["Total_bedrooms[32,23,1,16,49]"],["Population[3204,234563,3531,53316,35649]"], ["Households[3204,4563,3531,3316,5349]"], ["Median_income[4,11,6,3,14]"]]

# Step 6.2: Define different output components
# a. define text data type
output_module1 = gr.outputs.Textbox(label = "Predicted Housing Prices")

# b. define image data type
output_module2 = gr.outputs.Image(label = "Output Image")

# you can define more output components
import pandas as pd
import numpy as np

housing = pd.read_csv('/housing-2.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(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


## 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

## Step 1: training the data using decision tree algorithm
from sklearn.tree import DecisionTreeRegressor ## import the DecisionTree Function
tree_reg = DecisionTreeRegressor(random_state=42) ## Initialize the class
tree_reg.fit(train_features_normalized, train_labels) # feed the training data X, and label Y for supervised learning

### Step 2: make a prediction using tree model
training_predictions_trees = tree_reg.predict(train_features_normalized)
training_predictions_trees

def predict_house(input1, input2, input3, input4, input5, input6, input7, input8):
  input_features = list(input1, input2, input3, input4, input5, input6, input7, input8)
  scaler = MinMaxScaler() ## define the transformer
  scaler.fit(input_features)
  input_features_normalized = scaler.transform(input_features)
  output_predictions = tree_reg.predict(input_features_normalized)
  
  import matplotlib as plt
  from numpy import asarray
  from PIL import Image
  train_set.plot(kind="scatter", x="longitude", y="latitude", alpha=0.4, s=train_set["population"]/100, label="population", figsize=(10,7),
                 c="median_house_value", cmap=plt.get_cmap("jet"), colorbar=True,sharex=False)
  plt.legend()
  plt.plot(input_features[0], input_features[1], 'r*', markersize=25)
  graph = plt.show()
  return output_predictions[0], graph

# Step 6.4: Put all three component together into the gradio's interface function 
#gr.Label('CSCI4750/5750 Demo 3: Web Application for Housing Price Prediction')
#gr.HTML(show_label= 'CSCI4750/5750 Demo 3: Web Application for Housing Price Prediction')
gr.Interface(fn=predict_house, 
             inputs=[input_module1, input_module2, input_module3,
                     input_module4, input_module5, input_module6,
                     input_module7, input_module8], 
             outputs=[output_module1, output_module2], examples = examples ).launch()