In [ ]:
%pylab
%matplotlib inline
import pandas as pd
from pandas import DataFrame, Series
import json
import seaborn as sns
import IPython
from IPython.display import Image, display
pd.set_option('display.max_rows', 500)
pd.set_option('display.max_columns', 500)
pd.set_option('display.mpl_style', 'default') # Make the graphs a bit prettier
sns.set_style("darkgrid")
sns.set_palette("bright")
plt.rcParams['figure.figsize'] = (13, 9)
plt.rcParams['font.family'] = 'sans-serif'
import statsmodels.api as sm
import statsmodels.formula.api as smf
In [ ]:
advertdata = pd.read_table('../../DSUR/06/Advert.dat')
advertdata
In [ ]:
plt.scatter(np.arange(5), advertdata.adverts)
plt.plot([-1,5],[mean(advertdata.adverts),mean(advertdata.adverts)])
plt.scatter(np.arange(5), advertdata.packets, c="red")
plt.plot([-1,5],[mean(advertdata.packets),mean(advertdata.packets)], c="red", )
plt.show()
In [ ]:
sum(
(advertdata.adverts - mean(advertdata.adverts))* \
(advertdata.packets - mean(advertdata.packets)) \
) \
/(len(advertdata.adverts)-1)
In [ ]:
4.25 / (std(advertdata.adverts, ddof=1) * std(advertdata.packets, ddof=1))
In [ ]:
print .8711**2
advertdata.corr()
In [ ]:
advertdata.corr(method="spearman")
In [ ]:
examdata = pd.read_table('../../DSUR/06/Exam Anxiety.dat')
examdata.head(10)
In [ ]:
examdata[['Exam','Anxiety','Revise']].corr()
In [ ]:
from scipy.stats import pearsonr
print(pearsonr(examdata.Exam, examdata.Anxiety))
print(pearsonr(examdata.Exam, examdata.Revise))
print(pearsonr(examdata.Revise, examdata.Anxiety))
In [ ]:
examdata[['Exam','Anxiety','Revise']].corr(method='spearman')
In [ ]:
from scipy.stats import spearmanr
print(spearmanr(examdata.Exam, examdata.Anxiety))
print(spearmanr(examdata.Exam, examdata.Revise))
print(spearmanr(examdata.Revise, examdata.Anxiety))
In [ ]: