rodrigols89

import pandas as pd
pd.set_option('display.max_columns', 42)

data = pd.read_csv('../datasets/2015-building-energy-benchmarking.csv')

# Exibe a média de cada coluna.
print((data.isnull().sum() / len(data['OSEBuildingID'])) * 100, '\n')

data['ENERGYSTARScore'] = data['ENERGYSTARScore'].fillna(data['ENERGYSTARScore'].median())

rodrigols89

import pandas as pd
pd.set_option('display.max_columns', 18)

data = pd.read_csv('../datasets/athlete_events.csv')
data['Height'] = data['Height'].fillna(data['Height'].mean())
data['Weight'] = data['Weight'].fillna(data['Weight'].mean())

print(data[['Height', 'Weight']].head(20))

rodrigols89

import pandas as pd
pd.set_option('display.max_columns', 18)

data = pd.read_csv('../datasets/athlete_events.csv')
data['Medal'] = data['Medal'].fillna('Nenhuma')

print(data['Medal'].head(10))

rodrigols89

import pandas as pd
pd.set_option('display.max_columns', 18)

data = pd.read_csv('../datasets/athlete_events.csv')
percentMissing = (data.isnull().sum() / len(data['ID'])) * 100

print(percentMissing)

rodrigols89

import pandas as pd
pd.set_option('display.max_columns', 18)

data = pd.read_csv('../datasets/athlete_events.csv')
isNullSum = data.isnull().sum()

print(isNullSum)

rodrigols89

import pandas as pd
pd.set_option('display.max_columns', 18)

data = pd.read_csv('../datasets/athlete_events.csv')
isnull = data.isnull()

print(isnull)

rodrigols89

import pandas as pd
pd.set_option('display.max_columns', 18)

data = pd.read_csv('../datasets/athlete_events.csv')
dt = data.dropna()

print("Full sample: {0}".format(data.shape))
print("Sample without NaN: {0}".format(dt.shape))

rodrigols89

import pandas as pd
pd.set_option('display.max_columns', 18)

data = pd.read_csv('../datasets/athlete_events.csv')
dt = data.dropna()

print(dt.head())

rodrigols89

import pandas as pd
pd.set_option('display.max_columns', 18)

data = pd.read_csv('../datasets/athlete_events.csv')

print(data.head())
print(data.dtypes)

rodrigols89

import pandas as pd
pd.set_option('display.max_columns', 42)

data = pd.read_csv('../datasets/2015-building-energy-benchmarking.csv')

data['DataYear'] = data['DataYear'].astype(object)
print(data.dtypes)