Chapter1 GDP的预测和计算

#chapter1
import os
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import sklearn.linear_model
import csv


#load data
oecd_bli = pd.read_csv(r'D:\Github_Blog\handson-ml2\datasets\lifesat\oecd_bli_2015.csv',thousands=',')
gdp_per_capita = pd.read_csv(r'D:\Github_Blog\handson-ml2\datasets\lifesat\gdp_per_capita.csv',thousands=',',delimiter='\t',encoding='latin1',na_values="n/a")

#prepare data
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))
    return full_country_stats[["GDP per capita", 'Life satisfaction']].iloc[keep_indices]

country_stas = prepare_country_stats(oecd_bli,gdp_per_capita)
x = np.c_[country_stas['GDP per capita']]
y = np.c_[country_stas['Life satisfaction']]

#visulize the data
country_stas.plot(kind='scatter',x='GDP per capita',y='Life satisfaction')
plt.show()

#select a linear model
model.fix(x,y) 

#make a prediction for Cyprus
X_new = [[22587]]#Cyprus's gdp per capita
print(model.predict(X_new))#outputs