#!/usr/bin/env python
import pandas as pd
from printheader import print_header
cols = ['alpha', 'beta', 'gamma', 'delta', 'epsilon'] # <1>
indices = ['a', 'b', 'c', 'd', 'e', 'f'] # <2>
values = [ # <3>
[100, 110, 120, 130, 140],
[200, 210, 220, 230, 240],
[300, 310, 320, 330, 340],
[400, 410, 420, 430, 440],
[500, 510, 520, 530, 540],
[600, 610, 620, 630, 640],
]
print_header('cols')
print(cols, '\n')
print_header('indices')
print(indices, '\n')
print_header('values')
print(values, '\n')
df = pd.DataFrame(values, index=indices, columns=cols) # <4>
print_header('DataFrame df')
print(df, '\n')
print_header("df['gamma']")
print(df['alpha':'gamma']) # <5>
print(df['b':'e']) # <5>
#!/usr/bin/env python
import pandas as pd
from printheader import print_header
index1 = pd.Index(['a', 'b', 'c'], name='letters') # <1>
index2 = pd.Index(['b', 'a', 'c'])
index3 = pd.Index(['b', 'c', 'd'])
index4 = pd.Index(['red', 'blue', 'green'], name='colors')
print_header("index1, index2, index3", 70) # <2>
print(index1)
print(index2)
print(index3)
print()
print_header("index2 & index3", 70)
# these are the same
print(index2 & index3) # <3>
print(index2.intersection(index3)) # <3>
print()
print_header("index2 | index3", 70)
# these are the same
print(index2 | index3) # <4>
print(index2.union(index3))
print()
print_header("index1.difference(index3)", 70)
print(index1.difference(index3)) # <5>
print()
Created on Sun May 19 20:42:32 2013
'''
from pandas.core.frame import DataFrame
from printheader import print_header
cols = ['alpha','beta','gamma','delta','epsilon']
index = ['a','b','c','d','e','f']
values = [
[100, 110, 120, 130, 140],
[200, 210, 220, 230, 240],
[300, 310, 320, 330, 340],
[400, 410, 420, 430, 440],
[500, 510, 520, 530, 540],
[600, 610, 620, 630, 640],
]
print_header('values:')
print(values, '\n\n')
df = DataFrame(values, index=index, columns=cols)
print_header('DataFrame df')
print(df, '\n')
df2 = df.drop(['beta','delta'], axis=1)
print_header("After dropping beta and delta:")
print(df2, '\n')
print_header("After dropping rows b, c, and e")
df3 = df.drop(['b','c','e'], axis=0)
print(df3)
from pandas.core.frame import DataFrame
from printheader import print_header # <1>
dataset1 = np.arange(9.).reshape((3, 3)) # <2>
df1 = DataFrame( # <3>
dataset1,
columns=['apple', 'banana', 'mango'],
index=['orange', 'purple', 'blue'])
dataset2 = np.arange(12.).reshape((4, 3)) # <2>
df2 = DataFrame( # <3>
dataset2,
columns=['apple', 'banana', 'kiwi'],
index=['orange', 'purple', 'blue', 'brown'])
print_header('df1')
print(df1) # <4>
print()
print_header('df2')
print(df2) # <4>
print()
print_header('df1 + df2')
print(df1 + df2) # <5>
print_header('df1.add(df2, fill_value=0)')
print(df1.add(df2, fill_value=0)) # <6>
from pandas.core.frame import DataFrame
from printheader import print_header
cols = ['alpha', 'beta', 'gamma', 'delta', 'epsilon']
index = ['a', 'b', 'c', 'd', 'e', 'f']
values = [
[100, 110, 120, 130, 140],
[200, 210, 220, 230, 240],
[300, 310, 320, 330, 340],
[400, 410, 420, 430, 440],
[500, 510, 520, 530, 540],
[600, 610, 620, 630, 640],
]
df = DataFrame(values, index=index, columns=cols)
print_header('DataFrame df')
print(df, '\n')
# select a column
print_header("df['alpha']:")
print(df['alpha'], '\n')
# same as above
print_header("df.alpha:")
print(df.alpha, '\n')
# slice rows
print_header("df['b':'e']")
print(df['b':'e'], '\n')
# single row
"""
@author: jstrick
Created on Sat May 18 11:36:57 2013
"""
import pandas as pd
from printheader import print_header
# data from
# http://www.rita.dot.gov/bts/sites/rita.dot.gov.bts/files/publications/
# national_transportation_statistics/html/table_01_44.html
airports_df = pd.read_csv('../DATA/airport_boardings.csv', thousands=',')
print_header("ENTIRE DATAFRAME")
print(airports_df, "\n")
print_header("ONLY COLUMN 'CODE'")
print(airports_df['Code'], "\n")
print_header("SELECTED COLUMNS WITH FILTERED ROWS")
columns_wanted = ['Code', '2001 Total', 'Airport']
sort_col = '2001 Total'
max_val = 20000000
selector = airports_df['2001 Total'] > max_val
print(airports_df[selector][columns_wanted])
print_header("COLUMN TOTALS")
print(airports_df[['2001 Total', '2010 Total']].sum(), "\n")
#!/usr/bin/env python
import pandas as pd
from printheader import print_header
# data from
# http://www.rita.dot.gov/bts/sites/rita.dot.gov.bts/files/publications/
# national_transportation_statistics/html/table_01_44.html
airports_df = pd.read_csv('../DATA/airport_boardings.csv', thousands=',', index_col=1) # <1>
print_header("HEAD OF DATAFRAME")
print(airports_df.head(), "\n")
print_header("SELECTED COLUMNS WITH FILTERED ROWS")
columns_wanted = ['2001 Total', 'Airport']
sort_col = '2001 Total'
max_val = 20000000
selector = airports_df['2001 Total'] > max_val
selected = airports_df[selector][columns_wanted]
print(selected)
print_header("COLUMN TOTALS")
print(airports_df[['2001 Total', '2010 Total']].sum(), "\n")
# print_header("'CODE' COLUMN SET AS INDEX")
# airports_df.set_index('Code')
# print(airports_df)
print_header("FIRST FIVE ROWS")
print(airports_df.iloc[:5])
print(index, "\n")
values = [
[100, 110, 120, 930, 140],
[250, 210, 120, 130, 840],
[300, 310, 520, 430, 340],
[275, 410, 420, 330, 777],
[300, 510, 120, 730, 540],
[150, 610, 320, 690, 640],
]
ser1 = Series([.1, .2, .3, .4, .5])
df = DataFrame(values, index, cols)
print_header("Basic DataFrame:")
print(df)
print()
print_header("Triple each column")
print(df * 3)
print()
print_header("Multiply column gamma by 1.5")
df['gamma'] *= 1.5
print(df)
print()
# print_header("Multiply by strings")
# df['gamma'] *= 'spam'
# print(df)
#!/usr/bin/env python
import pandas as pd
from printheader import print_header
col_names = ["Desc", "1960", "1965", "1970", "1975", "1980", "1985", "1990",
"1991", "1992", "1993", "1994", "1995", "1996", "1997", "1998",
"1999", "2000", "2001", "2002", "2003", "2004", "2005", "2006",
"2007", "2008", "2009", "(R) 2010", "2011"] # <1>
df = pd.read_csv( # <2>
'../DATA/energy_use_quad.csv',
names=col_names,
header=None,
index_col="Desc",
)
print_header("database header")
print(df.head(), "\n")
print("-" * 60)
print_header("Only column 2003")
print(df[:]['2003'], "\n") # <3>
print("-" * 60)
print_header('Only row "Transportation as percent..."')
print(df.loc['Transportation as percent of total energy consumption'])