cab938

#!pip install html5lib #install html5lib, only needs to be run once
import pandas as pd
import numpy as np
df=pd.read_html('https://proxy.mentoracademy.org/getContentFromUrl/?userid=brooks&url=https://en.wikipedia.org/wiki/List_of_natural_satellites', header=0)
moons=df[4][1:] #drop prehistoric moon sighting
moons=moons['Discovery year'] #we are only interested in the year discovered

moons=moons.apply(lambda x: x.split('/')[0]).astype(int) #clean dataframe to just years as ints
pre_2000=len(moons[moons<2000]) #select only that data from moons which is less than 2000
post_2000=len(moons[moons>=2000]) #select only that data from moons which is greater than or equal to 2000

cab938

#!pip install html5lib #install html5lib, only needs to be run once
import pandas as pd
import numpy as np
earthquake_data='https://proxy.mentoracademy.org/getContentFromUrl/?userid=brooks&url=https%3A%2F%2Fen.wikipedia.org%2Fwiki%2FList_of_earthquakes_in_the_United_States'
df = pd.read_html(earthquake_data, header=0)[0]

df=df[df['Magnitude']!='Unknown'] #get rid of all the data where there is no known magnitude
df['Magnitude']=df['Magnitude'].apply(lambda x: x.split(", ")[0]) #for data where there are two values report with a comma, just take the first value
df['Magnitude']=df['Magnitude'].apply(lambda x: np.mean(np.array(x.split('–')).astype(float))) #average all ranges of values
print(len(df[df['Magnitude']>7])) #print out how many earthquakes on this list had values >7

cab938

#!pip install html5lib #install html5lib, only needs to be run once
import pandas as pd
import numpy as np
df=pd.read_html('https://proxy.mentoracademy.org/getContentFromUrl/?userid=brooks&url=https://en.wikipedia.org/wiki/List_of_highest-grossing_Indian_films', header=0)
bollywood=df[5].head(10)['Worldwide gross']
tollywood=df[13].head(10)['Worldwide gross']
 
bolly_top=np.sum(bollywood.apply(lambda x: x.split('₹')[1].split(' ')[0].replace(',','')).astype(float))
tolly_top=np.sum(tollywood.apply(lambda x: x[1:x.find(' ')].replace(',','')).astype(float))

cab938

cab938

cab938

Rank,State or union territory,Population,Decadal growth (2001–2011),Rural pop.[16] (%),Urban pop.[16] (%),Area[17],Density,Sex ratio
1,Uttar Pradesh,207281477,20.1%,"7008155111022000000♠155,111,022 (77.72%)","7007444704550000000♠44,470,455 (22.28%)","7011240928000000000♠240,928 km2 (93,023 sq mi)","6996828000000000000♠828/km2 (2,140/sq mi)",908
2,Maharashtra,112372972,16.0%,"7007615454410000000♠61,545,441 (54.77%)","7007508275310000000♠50,827,531 (45.23%)","7011307713000000000♠307,713 km2 (118,809 sq mi)",6996365000000000000♠365/km2 (950/sq mi),946
3,Bihar,103804637,25.1%,"7007920750280000000♠92,075,028 (88.70%)","7007117296090000000♠11,729,609 (11.30%)","7010941630000000000♠94,163 km2 (36,357 sq mi)","6997110199999999999♠1,102/km2 (2,850/sq mi)",916
4,West Bengal,91347736,13.9%,"7007622136760000000♠62,213,676 (68.11%)","7007291340600000000♠29,134,060 (31.89%)","7010887520000000000♠88,752 km2 (34,267 sq mi)","6997102900000000000♠1,029/km2 (2,670/sq mi)",947
5,Madhya Pradesh,72597565,20.3%,"7007525378990000000

cab938

cab938

#!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

cab938

#!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%2Ffb463f56781fae4dd1fc171def0f1e94%2Fraw%2Fa6a7e255dadb09a29cf05de692fc16b4c09e941c%2Findia_power.csv')
df_states=pd.read_csv('https://proxy.mentoracademy.org/getContentFromUrl/?userid=brooks&url=https%3A%2F%2Fgist.github.com%2Fcab938%2Ff8862f40901442ae61b458327d13ef9f%2Fraw%2F13dff6567589592828ee15778d0d5897cf09f335%2Findia_states.csv')

joined_df=pd.merge(df_states, df_power, left_on=["State or union territory"], right_on=["State"], how="inner") #join frames and only consider places we have data for both the state pop and renewables

cab938