Last active
April 21, 2018 17:22
-
-
Save cab938/f84d8429dd58c106cd6d54b072ce9851 to your computer and use it in GitHub Desktop.
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
#!pip install html5lib #install html5lib, only needs to be run once | |
#You might need to restart kernel after running with the menu Kernel>Restart | |
import pandas as pd | |
import numpy as np | |
df_power=pd.read_csv('https://proxy.mentoracademy.org/getContentFromUrl/?userid=brooks&url=https%3A%2F%2Fgist.github.com%2Fcab938%2F71e8371ebc621a105afa2181efd78e75%2Fraw%2Ffafe9712373ab5a1d3b2fdb6ac09a28cbcfe8f82%2Fus_power.csv') | |
df_states=pd.read_csv('https://proxy.mentoracademy.org/getContentFromUrl/?userid=brooks&url=https%3A%2F%2Fgist.github.com%2Fcab938%2Ffaedc9046a01b2170c0b252fbc4fc416%2Fraw%2Ff5fa5974e7fef6b996e8ff8583f8d5b47ce391c5%2Fus_states.csv') | |
joined_df=pd.merge(df_states, df_power, left_on=["state"], right_on=["state"], how="inner") #join frames and only consider places we have data for both the state pop and renewables | |
def pct_renw_by_pop(x): | |
#print(x['renewables in GWh']) | |
return float(x['renewables in GWh'])/float(x['population']) | |
joined_df['renw_by_pop']= joined_df.apply(pct_renw_by_pop ,axis=1) #apply the function above to create a new column | |
joined_df['renw_by_pop_rank']= joined_df['renw_by_pop'].rank(ascending=False) #determine the ranks for each state in a new column | |
joined_df.sort_values(by='renw_by_pop_rank').head(5) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment