import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import sklearn.linear_model
import os
import sklearn.neighbors
import gradio as gr

datapath = os.path.join("datasets", "lifesat", "")
# Download the data
import urllib.request
# DOWNLOAD_ROOT = "https://raw.githubusercontent.com/ageron/handson-ml/master/"
# os.makedirs(datapath, exist_ok=True)
# for filename in ("oecd_bli_2015.csv", "gdp_per_capita.csv"):
#   print("Downloading", filename)
#   url = DOWNLOAD_ROOT + "datasets/lifesat/" + filename
#   urllib.request.urlretrieve(url, datapath + filename)

def prepare_country_stats(oecd_bli, gdp_per_capita):
  oecd_bli = oecd_bli[oecd_bli["INEQUALITY"]=="TOT"]
  oecd_bli = oecd_bli.pivot(index="Country", columns="Indicator",values="Value")
  gdp_per_capita.rename(columns={"2015": "GDP per capita"}, inplace=True)
  gdp_per_capita.set_index("Country", inplace=True)
  full_country_stats = pd.merge(left=oecd_bli, right=gdp_per_capita,
  left_index=True, right_index=True)
  full_country_stats.sort_values(by="GDP per capita", inplace=True)
  
  remove_indices = [0, 1, 6, 8, 33, 34, 35]
  keep_indices = list(set(range(36)) - set(remove_indices))
  # print(full_country_stats.head())
  return full_country_stats[["GDP per capita", 'Life satisfaction']].iloc[keep_indices]

# oecd_bli = pd.read_csv(datapath + "oecd_bli_2015.csv", thousands=',')
# gdp_per_capita = pd.read_csv(datapath + "gdp_per_capita.csv",thousands=',',delimiter='\t',
# encoding='latin1', na_values="n/a")

oecd_bli = pd.read_csv("oecd_bli_2015.csv", thousands=',')
gdp_per_capita = pd.read_csv("gdp_per_capita.csv",thousands=',',delimiter='\t',
encoding='latin1', na_values="n/a")


country_stats = prepare_country_stats(oecd_bli, gdp_per_capita)
X = np.c_[country_stats["GDP per capita"]]
y = np.c_[country_stats["Life satisfaction"]]

models = []
# Select a linear model
model1 = sklearn.neighbors.KNeighborsRegressor(n_neighbors=1)
model1.fit(X, y)
models.append(model1)

model2 = sklearn.neighbors.KNeighborsRegressor(n_neighbors=2)
model2.fit(X, y)
models.append(model2)

model3 = sklearn.neighbors.KNeighborsRegressor(n_neighbors=3)
model3.fit(X, y)
models.append(model3)

model4 = sklearn.neighbors.KNeighborsRegressor(n_neighbors=4)
model4.fit(X, y)
models.append(model4)

model5 = sklearn.neighbors.KNeighborsRegressor(n_neighbors=5)
model5.fit(X, y)
models.append(model5)

model6 = sklearn.neighbors.KNeighborsRegressor(n_neighbors=6)
model6.fit(X, y)
models.append(model6)

model7 = sklearn.neighbors.KNeighborsRegressor(n_neighbors=7)
model7.fit(X, y)
models.append(model7)

model8 = sklearn.neighbors.KNeighborsRegressor(n_neighbors=8)
model8.fit(X, y)
models.append(model8)

model9 = sklearn.neighbors.KNeighborsRegressor(n_neighbors=9)
model9.fit(X, y)
models.append(model9)





import gradio as gr

def sentence_builder(gdp, value_of_k):
    # return f"""The Value of Happiness for {gdp} and K = {value_of_k} is {models[int(value_of_k)].predict([[gdp]])[0][0]}"""
     return f"""The Value of Happiness for {gdp} and K = {value_of_k} is {models[int(value_of_k) - 1].predict([[gdp]])[0][0]}"""


demo = gr.Interface(
    sentence_builder,
    [
        gr.Slider(0, 99999, value=4),
        gr.Dropdown([1, 2, 3, 4, 5, 6, 7, 8, 9]),
    ],
    "text",
    examples=[
        [2000, 1],
        [5508, 5],
    ],
)

demo.launch()