In [1]:
import pandas as pd
from pandas import Series,DataFrame
import numpy as np
In [2]:
import matplotlib.pyplot as plt
import seaborn as sns
sns.set_style('whitegrid')
%matplotlib inline
In [3]:
from __future__ import division
In [4]:
import requests
In [5]:
from StringIO import StringIO
In [6]:
url = 'http://elections.huffingtonpost.com/pollster/2012-general-election-romney-vs-obama.csv'
source = requests.get(url).text
poll_data = StringIO(source)
In [7]:
poll_df = pd.read_csv(poll_data)
In [8]:
poll_df.info()
In [9]:
poll_df.head()
Out[9]:
In [10]:
sns.factorplot('Affiliation',data=poll_df,kind='count')
Out[10]:
In [11]:
sns.factorplot('Affiliation',data=poll_df,hue='Population',kind='count')
Out[11]:
In [12]:
poll_df.head()
Out[12]:
In [13]:
avg = pd.DataFrame(poll_df.mean())
avg.drop('Number of Observations',axis=0,inplace=True)
In [14]:
avg.head()
Out[14]:
In [15]:
std = pd.DataFrame(poll_df.std())
std.drop('Number of Observations',axis=0,inplace=True)
In [16]:
std.head()
Out[16]:
In [17]:
avg.plot(yerr=std,kind='bar',legend=False)
Out[17]:
In [18]:
poll_avg = pd.concat([avg,std],axis=1)
In [19]:
poll_avg.columns = ['Average','STD']
In [20]:
poll_avg
Out[20]:
In [ ]:
In [ ]:
In [ ]:
In [21]:
poll_df.head()
Out[21]:
In [22]:
poll_df.plot(x='End Date',y=['Obama','Romney','Undecided'],linestyle='',marker='o')
Out[22]:
In [23]:
from datetime import datetime
In [24]:
poll_df['Difference']=(poll_df.Obama-poll_df.Romney)/100
poll_df.head()
Out[24]:
In [25]:
poll_df=poll_df.groupby(['Start Date'],as_index=False).mean()
poll_df.head()
Out[25]:
In [26]:
poll_df.plot('Start Date','Difference',figsize=(12,4),marker='o',linestyle='-',color='purple')
Out[26]:
In [28]:
row_in=0
xlimit=[]
for date in poll_df['Start Date']:
if date[0:7]=='2012-10':
xlimit.append(row_in)
row_in+=1
else:
row_in+=1
print min(xlimit)
print max(xlimit)
In [34]:
poll_df.plot('Start Date','Difference',figsize=(12,4),marker='o',linestyle='-',color='purple',xlim=(329,356))
# Oct 3rd
plt.axvline(x=329+2,linewidth=4,color='grey')
# Oct 11th
plt.axvline(x=329+10,linewidth=4,color='grey')
# Oct 22nd
plt.axvline(x=329+21,linewidth=4,color='grey')
Out[34]:
In [ ]:
In [ ]:
In [ ]:
In [97]:
pwd
Out[97]:
In [98]:
donor_df = pd.read_csv('Election_Donor_Data.csv')
In [99]:
donor_df.info()
In [100]:
donor_df.head()
Out[100]:
In [101]:
donor_df['contb_receipt_amt'].value_counts()
Out[101]:
In [102]:
don_mean = donor_df['contb_receipt_amt'].mean()
don_std = donor_df['contb_receipt_amt'].std()
print 'The average donation was %.2f with a std %.2f' %(don_mean,don_std)
In [103]:
top_donor = donor_df['contb_receipt_amt'].copy()
top_donor.sort_index()
#top_donor.sort_values()
top_donor
Out[103]:
In [104]:
top_donor = top_donor[top_donor > 0]
top_donor.sort_index()
Out[104]:
In [105]:
top_donor.value_counts().head(10)
Out[105]:
In [106]:
com_don = top_donor[top_donor < 2500]
com_don.hist(bins=100,)
Out[106]:
In [ ]:
In [ ]:
In [ ]:
In [107]:
candidates = donor_df.cand_nm.unique()
candidates
Out[107]:
In [108]:
party_map = {'Bachmann, Michelle': 'Republican',
'Cain, Herman': 'Republican',
'Gingrich, Newt': 'Republican',
'Huntsman, Jon': 'Republican',
'Johnson, Gary Earl': 'Republican',
'McCotter, Thaddeus G': 'Republican',
'Obama, Barack': 'Democrat',
'Paul, Ron': 'Republican',
'Pawlenty, Timothy': 'Republican',
'Perry, Rick': 'Republican',
"Roemer, Charles E. 'Buddy' III": 'Republican',
'Romney, Mitt': 'Republican',
'Santorum, Rick': 'Republican'}
donor_df['Party']=donor_df.cand_nm.map(party_map)
In [109]:
donor_df=donor_df[donor_df.contb_receipt_amt > 0]
In [110]:
donor_df.head()
Out[110]:
In [111]:
donor_df.groupby('cand_nm')['contb_receipt_amt'].count()
Out[111]:
In [112]:
donor_df.groupby('cand_nm')['contb_receipt_amt'].sum()
Out[112]:
In [113]:
cand_amount=donor_df.groupby('cand_nm')['contb_receipt_amt'].sum()
i=0
for don in cand_amount:
print ' The candidate %s raise %.0f dolloars' %(cand_amount.index[i],don)
print ''
i+=1
In [114]:
cand_amount.plot(kind='bar')
Out[114]:
In [115]:
donor_df.groupby('Party')['contb_receipt_amt'].sum().plot(kind='bar')
Out[115]:
In [116]:
occupation_df=donor_df.pivot_table('contb_receipt_amt',
index='contbr_occupation',
columns='Party',
aggfunc='sum')
In [117]:
occupation_df.head()
Out[117]:
In [118]:
occupation_df.tail()
Out[118]:
In [119]:
occupation_df.shape
Out[119]:
In [120]:
occupation_df=occupation_df[occupation_df.sum(1) > 1000000]
In [121]:
occupation_df.shape
Out[121]:
In [122]:
occupation_df.plot(kind='bar')
Out[122]:
In [123]:
occupation_df.plot(kind='barh',figsize=(10,12),cmap='seismic')
Out[123]:
In [124]:
occupation_df.drop(['INFORMATION REQUESTED PER BEST EFFORTS','INFORMATION REQUESTED'],axis=0,inplace=True)
In [125]:
occupation_df.loc['CEO']=occupation_df.loc['CEO']+occupation_df.loc['C.E.O.']
occupation_df.drop('C.E.O.',inplace=True)
In [126]:
occupation_df.plot(kind='barh',figsize=(10,12),cmap='seismic')
Out[126]:
In [ ]: