8*6

2**16

2**\
6

2**0.5

from numpy import sqrt
sqrt(2)

abs(-65)

help(sqrt)

SquareRoot2 = sqrt(2)
SquareRoot2

HoursYear = 365*24
HoursYear

dir()[:5]

'HoursYear' in dir()

locals().keys()[:5]

'HoursYear' in locals().keys()

import numpy as np
np.array([2,3,5,8,13])

Country = np.array(["Brazil", "China", "India","Switzerland","USA"])
LifeExpectancy = np.array([74,76,65,83,79])
Country

print Country

print LifeExpectancy

Country[0]

LifeExpectancy[2]

Sequence = np.arange(0,100+1,2)
Sequence

from pandas import DataFrame
CountryData = DataFrame({'Country':Country, 'LifeExpectancy':LifeExpectancy})
print CountryData

CountryData['Population'] = np.array([199000,1390000,1240000,7997,318000])
print CountryData

Country = np.array(['Australia','Greece'])
LifeExpectancy = np.array([82, 81])
Population = np.array([23050, 11125])

NewCountryData = DataFrame({'Country':Country, 'LifeExpectancy':LifeExpectancy,
        'Population':Population})

print NewCountryData

AllCountryData = CountryData.append(NewCountryData)
print AllCountryData

AllCountryData.index = range(len(AllCountryData))
print AllCountryData

print CountryData.append(NewCountryData, True)

import os
path = 'C:\\Users\\iris\\documents\\github\\edX\\The Analytic Edge\\week1'
os.chdir(path)

import pandas as pd
WHO = pd.read_csv("WHO.csv")

WHO.head()

print WHO.shape

print WHO.dtypes

print WHO.values.T[:,:5]

WHO.describe(include = 'all')

WHO_Europe =  WHO[WHO.Region == "Europe"]
WHO_Europe.shape

WHO_Europe.to_csv("WHO_Europe.csv")

del(WHO_Europe)

WHO['Under15'].mean()

WHO['Under15'].std()

WHO['Under15'].describe()

WHO['Under15'].idxmin()

WHO['Country'][85]

WHO['Under15'].idxmax()

WHO.at[123,'Country']

WHO.plot('GNI', 'FertilityRate', kind = 'scatter')

Outliers = WHO[(WHO.GNI > 10000) & (WHO.FertilityRate > 2.5)]
Outliers.shape[0]

Outliers[['Country','GNI','FertilityRate']]

WHO.plot(y = 'CellularSubscribers', kind = 'hist', legend = False)

WHO.boxplot('LifeExpectancy', by = 'Region')

fig = plt.figure()
WHO.boxplot('LifeExpectancy', by = 'Region', rot = 60)
plt.title("Life Expectancy of Countries by Region")
plt.suptitle("")
plt.ylabel("Life Expectancy")

WHO.groupby('Region').size()

WHO.groupby('Region')['Over60'].mean()

WHO.groupby('Region')['LiteracyRate'].min()