Intro to Pandas Data Structures


%auto
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

%auto
# so that numbers are Python by default, not sage, which would confuse pandas.
%default_mode python

# make all output look nice, e.g., html tables, without havig to explicitly type show.
%typeset_mode True

# create a Series with an arbitrary list
s = pd.Series([7, 'Heisenberg', 3.14, -1789710578, 'Happy Eating!'])
s

              7
     Heisenberg
           3.14
    -1789710578
  Happy Eating!
dtype: object

# Arbitrary index
s = pd.Series([7, 'Heisenberg', 3.14, -1789710578, 'Happy Eating!'],
              index=['A', 'Z', 'C', 'Y', 'E'])
s

A                7
Z       Heisenberg
C             3.14
Y      -1789710578
E    Happy Eating!
dtype: object

d = {'Chicago': 1000, 'New York': 1300, 'Portland': 900, 'San Francisco': 1100,
     'Austin': 450, 'Boston': None}
cities = pd.Series(d)
cities

Austin            450.0
Boston              NaN
Chicago          1000.0
New York         1300.0
Portland          900.0
San Francisco    1100.0
dtype: float64

(cities < 1000)

Austin            True
Boston           False
Chicago          False
New York         False
Portland          True
San Francisco    False
dtype: bool

cities[cities < 1000]

Austin      450.0
Portland    900.0
dtype: float64

cities[cities < 1000] = 750
cities[cities < 1000]
print
cities

Austin      750.0
Portland    750.0
dtype: float64

Austin            750.0
Boston              NaN
Chicago          1000.0
New York         1300.0
Portland          750.0
San Francisco    1100.0
dtype: float64

"Austin" in cities
"Seattle" in cities

\displaystyle \mathrm{True}

\displaystyle \mathrm{False}

cities["Seattle"] = 200
print "Seattle" in cities
print
cities

True

Austin            750.0
Boston              NaN
Chicago          1000.0
New York         1300.0
Portland          750.0
San Francisco    1100.0
Seattle           200.0
dtype: float64

Dataframes

data = {'year': [2010, 2011, 2012, 2011, 2012, 2010, 2011, 2012],
        'team': ['Bears', 'Bears', 'Bears', 'Packers', 'Packers', 'Lions', 'Lions', 'Lions'],
        'wins': [11, 8, 10, 15, 11, 6, 10, 4],
        'losses': [5, 8, 6, 1, 5, 10, 6, 12]}
football = pd.DataFrame(data, columns=['year', 'team', 'wins', 'losses'])
football

	year	team	wins	losses
0	2010	Bears	11	5
1	2011	Bears	8	8
2	2012	Bears	10	6
3	2011	Packers	15	1
4	2012	Packers	11	5
5	2010	Lions	6	10
6	2011	Lions	10	6
7	2012	Lions	4	12


football.to_excel('football.xlsx', index=False)

Error in lines 1-1
Traceback (most recent call last):
  File "/projects/sage/sage-6.10/local/lib/python2.7/site-packages/smc_sagews/sage_server.py", line 905, in execute
    exec compile(block+'\n', '', 'single') in namespace, locals
  File "", line 1, in <module>
  File "/projects/sage/sage-6.10/local/lib/python2.7/site-packages/pandas/core/frame.py", line 1414, in to_excel
    excel_writer = ExcelWriter(excel_writer, engine=engine)
  File "/projects/sage/sage-6.10/local/lib/python2.7/site-packages/pandas/io/excel.py", line 713, in __init__
    if not openpyxl_compat.is_compat(major_ver=self.openpyxl_majorver):
  File "/projects/sage/sage-6.10/local/lib/python2.7/site-packages/pandas/compat/openpyxl_compat.py", line 27, in is_compat
    import openpyxl
ImportError: No module named openpyxl

url = 'https://raw.github.com/gjreda/best-sandwiches/master/data/best-sandwiches-geocode.tsv'

# fetch the text from the URL and read it into a DataFrame
from_url = pd.read_table(url, sep='\t')
from_url.head(3)

	rank	sandwich	restaurant	description	price	address	city	phone	website	full_address	formatted_address	lat	lng
0	1	BLT	Old Oak Tap	The B is applewood smoked—nice and snapp...	$10	2109 W. Chicago Ave.	Chicago	773-772-0406	theoldoaktap.com	2109 W. Chicago Ave., Chicago	2109 West Chicago Avenue, Chicago, IL 60622, USA	41.895734	-87.679960
1	2	Fried Bologna	Au Cheval	Thought your bologna-eating days had retired w...	$9	800 W. Randolph St.	Chicago	312-929-4580	aucheval.tumblr.com	800 W. Randolph St., Chicago	800 West Randolph Street, Chicago, IL 60607, USA	41.884672	-87.647754
2	3	Woodland Mushroom	Xoco	Leave it to Rick Bayless and crew to come up w...	$9.50.	445 N. Clark St.	Chicago	312-334-3688	rickbayless.com	445 N. Clark St., Chicago	445 North Clark Street, Chicago, IL 60654, USA	41.890602	-87.630925

︠2cbc9700-d027-463f-9b95-b18ebd90289b︠