import numpy as np import pandas as pd

# A structured array my_array = np.ones(3, dtype=([('foo',int), ('bar',float)])) print(my_array['foo'])

# A record array my_array2 = my_array.view(np.recarray) print(my_array2.bar)

s = pd.Series(np.random.randn(5), index = ['a','b','c','d','e']) print(s)

d = {'one': [1., 2., 3., 4.], 'two': [4., 3., 2., 1.]} df = pd.DataFrame(d) print(df)

data = np.array([['','Col1','Col2'], ['Row1',1,2], ['Row2',3,4]]) df = pd.DataFrame(data=data[1:,1:], index=data[1:,0], columns=data[0,1:]) data[1:,1:] data[1:,0] data[0,1:]

my_dict = {'First': ['1','3'], 'Second': ['1','2'], 'Third': ['2','4']} df = pd.DataFrame(my_dict) print(df)

bankData = pd.read_csv("bank-data.csv",sep=";") print(bankData.shape) bankData.info()

bankData.to_csv('test.csv')

df = pd.DataFrame(np.array([[1, 2, 3], [4, 5, 6]])) df

# Use the shape property print(df.shape)

# or use the len() function with the index property print(len(df.index))

df.index

bankData.head()

bankData.tail()

bankData.columns

bankData.describe()

bankData.sort_values(by='age').tail()

bankData['job'].head()

bankData.job

bankData[['job','age']].head()

bankData.loc[1:5,['job','age','education']]

bankData.iloc[:5,:3]

bankData[0:5]

bankData.marital.isin(['single'])

bankData[bankData.marital.isin(['single','married'])].head()

data = bankData[bankData.age > 30] data

data = data[data.marital.isin(['single','married']) & (data.age == 30)] data

oneColumn = np.ones(len(bankData)) print(oneColumn) bankData['one'] = oneColumn bankData.head()

del bankData['one'] bankData.head()

# Read flight data flightData = pd.read_csv('flights.csv',index_col=0) #del cases['Unnamed: 0'] flightData.head()

flightData.info()

# Show rows with missing data flightData[flightData.dep_delay.isnull()]

index_nan = flightData.dep_delay.index[flightData.dep_delay.isnull()] print(index_nan)

flightData.shape

flightData.dropna(how='any').shape

flightData.dropna(how='any').head()

flightData_dropNA = flightData.dropna(how='any') flightData_dropNA.head()

x = np.mean(flightData.dep_delay) print("%1.1f"%x)

#Show index of the missing data #index_nan = flightData.dep_delay.index[flightData.dep_delay.isnull()] flightData.fillna(value={'dep_delay':x}).loc[index_nan].head()

flightData_fillNA = flightData.fillna(value={'dep_delay':x}) flightData_fillNA

bankData.mean()

bankData.std()

bankData.median()

df = pd.DataFrame(np.array([[1,2,3], [4,5,6], [7,8,9]])) df.apply(np.cumsum, axis =0)

bankData.num = bankData._get_numeric_data() bankData.num.head()

bankData.num.columns bankData[bankData.num.columns] = bankData.num.apply(lambda x:x/x.max()) bankData.head()

pd.concat([bankData['age'],bankData['job']],axis = 1).head()

left = pd.DataFrame({'key': ['A', 'B'], 'lval': [1, 2]}) right = pd.DataFrame({'key': ['A', 'B'], 'rval': [4, 5]}) print(left) print(right)

join_df = pd.merge(left,right,on='key') join_df

bankData.groupby('job').mean()

bankData.groupby(['marital','education']).mean()

cases = pd.read_csv('cases.csv') cases

cases.melt(id_vars='country', value_vars=cases.columns[2:4], var_name = 'Year', value_name = 'n')

pollution = pd.read_csv('pollution.csv') pollution

pollution.pivot(index='city', columns='size', values='amount')

df = pd.DataFrame({'key': list('bbacab'), 'data1':range(6)}) df

pd.get_dummies(df['key'])

bankData.education

pd.get_dummies(bankData, columns=['education']).head()