Created
July 14, 2015 20:57
-
-
Save tomatau/045f8f59c0245b7f2335 to your computer and use it in GitHub Desktop.
tf-ds-u2-lesson2.2
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/python | |
import matplotlib.pyplot as plt | |
import pandas as pd | |
import scipy.stats as stats | |
# read the data | |
loansData = pd.read_csv( | |
'https://spark-public.s3.amazonaws.com/dataanalysis/loansData.csv' | |
) | |
# clean it | |
loansData.dropna(inplace=True) | |
col = 'Amount.Requested' | |
# generate a box plot and show it | |
loansData.boxplot(column=col, return_type='axes') | |
plt.show() | |
# generate a histogram and show it | |
loansData.hist(column=col) | |
plt.show() | |
# create a new figure | |
plt.figure() | |
# qq plot against normal | |
graph = stats.probplot( | |
loansData[col], dist="norm", plot=plt | |
) | |
plt.show() | |
# Amount.Requested and Amount.Funded.By.Investors are both fairly normal and roughly the same median | |
# Amount Funded By Investors has more of a positive tail | |
# and more spread (from 0 to 35000) but the mode is higher | |
# and the inner quartiles are closer to the median, | |
# especially the upper quartile, implying the mean is lower? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment