4. Filtering & Merging

Filtering of rows

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

import sklearn.linear_model

desired_width=320

pd.set_option('display.width', desired_width)

np.set_printoptions(linewidth=desired_width)

pd.set_option('display.max_columns',100)

url = 'https://raw.githubusercontent.com/nyp-sit/data/master/Better_Life.csv'

df = pd.read_csv(url)

print(df.head())

LOCATION Country INDICATOR Indicator MEASURE Measure INEQUALITY Inequality

0 AUS Australia JE_LMIS Labour market insecurity L Value TOT Total

1 AUT Austria JE_LMIS Labour market insecurity L Value TOT Total

2 BEL Belgium JE_LMIS Labour market insecurity L Value TOT Total

3 CAN Canada JE_LMIS Labour market insecurity L Value TOT Total

4 CZE Czech Republic JE_LMIS Labour market insecurity L Value TOT Total

life_df = df.loc[(df['Indicator'] == 'Life satisfaction') & (df['Inequality'] == 'Total')]

print(life_df.head())

LOCATION Country INDICATOR Indicator MEASURE Measure INEQUALITY Inequality

2859 AUS Australia SW_LIFS Life satisfaction L Value TOT Total

2860 AUT Austria SW_LIFS Life satisfaction L Value TOT Total

2861 BEL Belgium SW_LIFS Life satisfaction L Value TOT Total

2862 CAN Canada SW_LIFS Life satisfaction L Value TOT Total

2863 CZE Czech Republic SW_LIFS Life satisfaction L Value TOT Total

Merging

url1 = 'https://raw.githubusercontent.com/nyp-sit/data/master/WEO_Data.csv'

gdp_df = pd.read_csv(url1, encoding='latin-1', thousands=',')

print(gdp_df.head())

Country Subject Descriptor Units Scale 2015 Estimates Start After

0 Afghanistan Gross domestic product per capita, current prices U.S. dollars Units 599.994 2013.0

1 Albania Gross domestic product per capita, current prices U.S. dollars Units 3995.380 2010.0

2 Algeria Gross domestic product per capita, current prices U.S. dollars Units 4318.140 2014.0

3 Angola Gross domestic product per capita, current prices U.S. dollars Units 4100.320 2014.0

4 Antigua and Barbuda Gross domestic product per capita, current prices U.S. dollars Units 14414.300 2011.0

pdf = pd.merge(gdp_df[['Country', '2015']], life_df[['Country', 'Value']] , on='Country', how='inner')

pdf.rename(columns={'Value':'Life satisfaction','2015':'GDP per capita'}, inplace=True)

print(pdf.head())

Country GDP per capita Life satisfaction

0 Australia 50961.87 7.3

1 Austria 43724.03 7.0

2 Belgium 40106.63 6.9

3 Brazil 8670.00 6.6

4 Canada 43331.96 7.3

Linear Regression

X = np.c_[pdf['GDP per capita']]

y = np.c_[pdf['Life satisfaction']]

lin_reg_model = sklearn.linear_model.LinearRegression()

lin_reg_model.fit(X, y)

X_new = [[22587]]

print(lin_reg_model.predict(X_new))

[[6.24626326]]