iskm/learnxinyminutes-docs
1
0
Fork 0
mirror of https://github.com/adambard/learnxinyminutes-docs.git synced 2024-12-23 17:41:41 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

pep8 fixes (spaces and multiline statements)

Browse Source 
in Python readability and code style matters
This commit is contained in:
Piotr Migdał 2016-01-03 19:45:54 +01:00
parent b2113480a4
commit bde8645cc7
1 changed files with 55 additions and 44 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

63
pythonstatcomp.html.markdown
View File

@ -9,6 +9,8 @@ This is a tutorial on how to do some typical statistical programming tasks using
```python ```python
# 0. Getting set up ==== # 0. Getting set up ====
""" Get set up with IPython and pip install the following: numpy, scipy, pandas, """ Get set up with IPython and pip install the following: numpy, scipy, pandas,
@ -25,17 +27,17 @@ This is a tutorial on how to do some typical statistical programming tasks using
already using Python, there's a benefit to sticking with one language. already using Python, there's a benefit to sticking with one language.
""" """
import requests # for HTTP requests (web scraping, APIs) import requests # for HTTP requests (web scraping, APIs)
import os import os
# web scraping # web scraping
r = requests.get("https://github.com/adambard/learnxinyminutes-docs") r = requests.get("https://github.com/adambard/learnxinyminutes-docs")
r.status_code # if 200, request was successful r.status_code # if 200, request was successful
r.text # raw page source r.text # raw page source
print(r.text) # prettily formatted print(r.text) # prettily formatted
# save the page source in a file: # save the page source in a file:
os.getcwd() # check what's the working directory os.getcwd() # check what's the working directory
f = open("learnxinyminutes.html","wb") f = open("learnxinyminutes.html", "wb")
f.write(r.text.encode("UTF-8")) f.write(r.text.encode("UTF-8"))
f.close() f.close()
@ -44,7 +46,7 @@ fp = "https://raw.githubusercontent.com/adambard/learnxinyminutes-docs/master/"
fn = "pets.csv" fn = "pets.csv"
r = requests.get(fp + fn) r = requests.get(fp + fn)
print(r.text) print(r.text)
f = open(fn,"wb") f = open(fn, "wb")
f.write(r.text.encode("UTF-8")) f.write(r.text.encode("UTF-8"))
f.close() f.close()
@ -58,7 +60,9 @@ f.close()
you've used R, you will be familiar with the idea of the "data.frame" already. you've used R, you will be familiar with the idea of the "data.frame" already.
""" """
import pandas as pd, numpy as np, scipy as sp import pandas as pd
import numpy as np
import scipy as sp
pets = pd.read_csv(fn) pets = pd.read_csv(fn)
pets pets
# name age weight species # name age weight species
@ -74,20 +78,20 @@ pets
pets.age pets.age
pets["age"] pets["age"]
pets.head(2) # prints first 2 rows pets.head(2) # prints first 2 rows
pets.tail(1) # prints last row pets.tail(1) # prints last row
pets.name[1] # 'vesuvius' pets.name[1] # 'vesuvius'
pets.species[0] # 'cat' pets.species[0] # 'cat'
pets["weight"][2] # 34 pets["weight"][2] # 34
# in R, you would expect to get 3 rows doing this, but here you get 2: # in R, you would expect to get 3 rows doing this, but here you get 2:
pets.age[0:2] pets.age[0:2]
# 0 3 # 0 3
# 1 6 # 1 6
sum(pets.age)*2 # 28 sum(pets.age) * 2 # 28
max(pets.weight) - min(pets.weight) # 20 max(pets.weight) - min(pets.weight) # 20
""" If you are doing some serious linear algebra and number-crunching, you may """ If you are doing some serious linear algebra and number-crunching, you may
just want arrays, not DataFrames. DataFrames are ideal for combining columns just want arrays, not DataFrames. DataFrames are ideal for combining columns
@ -96,7 +100,8 @@ max(pets.weight) - min(pets.weight) # 20
# 3. Charts ==== # 3. Charts ====
import matplotlib as mpl, matplotlib.pyplot as plt import matplotlib as mpl
import matplotlib.pyplot as plt
%matplotlib inline %matplotlib inline
# To do data vizualization in Python, use matplotlib # To do data vizualization in Python, use matplotlib
@ -105,13 +110,17 @@ plt.hist(pets.age);
plt.boxplot(pets.weight); plt.boxplot(pets.weight);
plt.scatter(pets.age, pets.weight); plt.xlabel("age"); plt.ylabel("weight"); plt.scatter(pets.age, pets.weight)
plt.xlabel("age")
plt.ylabel("weight");
# seaborn sits atop matplotlib and makes plots prettier # seaborn sits atop matplotlib and makes plots prettier
import seaborn as sns import seaborn as sns
plt.scatter(pets.age, pets.weight); plt.xlabel("age"); plt.ylabel("weight"); plt.scatter(pets.age, pets.weight)
plt.xlabel("age")
plt.ylabel("weight");
# there are also some seaborn-specific plotting functions # there are also some seaborn-specific plotting functions
# notice how seaborn automatically labels the x-axis on this barplot # notice how seaborn automatically labels the x-axis on this barplot
@ -141,7 +150,7 @@ ggplot(aes(x="age",y="weight"), data=pets) + geom_point() + labs(title="pets")
url = "https://raw.githubusercontent.com/e99n09/R-notes/master/data/hre.csv" url = "https://raw.githubusercontent.com/e99n09/R-notes/master/data/hre.csv"
r = requests.get(url) r = requests.get(url)
fp = "hre.csv" fp = "hre.csv"
f = open(fp,"wb") f = open(fp, "wb")
f.write(r.text.encode("UTF-8")) f.write(r.text.encode("UTF-8"))
f.close() f.close()
@ -173,9 +182,9 @@ hre.head()
# clean the Birth and Death columns # clean the Birth and Death columns
import re # module for regular expressions import re # module for regular expressions
rx = re.compile(r'\d+$') # match trailing digits rx = re.compile(r'\d+$') # match trailing digits
""" This function applies the regular expression to an input column (here Birth, """ This function applies the regular expression to an input column (here Birth,
Death), flattens the resulting list, converts it to a Series object, and Death), flattens the resulting list, converts it to a Series object, and
@ -185,8 +194,9 @@ rx = re.compile(r'\d+$') # match trailing digits
- http://stackoverflow.com/questions/11860476/how-to-unlist-a-python-list - http://stackoverflow.com/questions/11860476/how-to-unlist-a-python-list
- http://pandas.pydata.org/pandas-docs/stable/generated/pandas.Series.html - http://pandas.pydata.org/pandas-docs/stable/generated/pandas.Series.html
""" """
def extractYear(v): def extractYear(v):
return(pd.Series(reduce(lambda x,y: x+y,map(rx.findall,v),[])).astype(int)) return(pd.Series(reduce(lambda x, y: x + y, map(rx.findall, v), [])).astype(int))
hre["BirthY"] = extractYear(hre.Birth) hre["BirthY"] = extractYear(hre.Birth)
hre["DeathY"] = extractYear(hre.Death) hre["DeathY"] = extractYear(hre.Death)
@ -199,17 +209,17 @@ sns.lmplot("BirthY", "EstAge", data=hre, hue="Dynasty", fit_reg=False);
# use scipy to run a linear regression # use scipy to run a linear regression
from scipy import stats from scipy import stats
(slope,intercept,rval,pval,stderr)=stats.linregress(hre.BirthY,hre.EstAge) (slope, intercept, rval, pval, stderr) = stats.linregress(hre.BirthY, hre.EstAge)
# code source: http://wiki.scipy.org/Cookbook/LinearRegression # code source: http://wiki.scipy.org/Cookbook/LinearRegression
# check the slope # check the slope
slope # 0.0057672618839073328 slope # 0.0057672618839073328
# check the R^2 value: # check the R^2 value:
rval**2 # 0.020363950027333586 rval**2 # 0.020363950027333586
# check the p-value # check the p-value
pval # 0.34971812581498452 pval # 0.34971812581498452
# use seaborn to make a scatterplot and plot the linear regression trend line # use seaborn to make a scatterplot and plot the linear regression trend line
sns.lmplot("BirthY", "EstAge", data=hre); sns.lmplot("BirthY", "EstAge", data=hre);
@ -223,6 +233,7 @@ sns.lmplot("BirthY", "EstAge", data=hre);
To see a version of the Holy Roman Emperors analysis using R, see To see a version of the Holy Roman Emperors analysis using R, see
- http://github.com/e99n09/R-notes/blob/master/holy_roman_emperors_dates.R - http://github.com/e99n09/R-notes/blob/master/holy_roman_emperors_dates.R
""" """
``` ```
If you want to learn more, get _Python for Data Analysis_ by Wes McKinney. It's a superb resource and I used it as a reference when writing this tutorial. If you want to learn more, get _Python for Data Analysis_ by Wes McKinney. It's a superb resource and I used it as a reference when writing this tutorial.