GApplication.py

import matplotlib.pyplot as plt
from numpy.random import normal, uniform
import pandas as pd
import os
os.listdir()

data = pd.read_csv("DSI.csv")

data.head()

%matplotlib inline

plt.hist(data.backers)
plt.title("Backers Hist")
plt.xlabel("Backers")
plt.ylabel("Frequency")
plt.show()

plt.hist(data.duration)
plt.title("Duration Hist")
plt.xlabel("Duration")
plt.ylabel("Frequency")
plt.show()

durationmean=data.duration.mean()
durationmean

durationstd=data.duration.std()
durationstd

nobs=len(data)
nobs

lensd1 = len(data.loc[(data.duration > (durationmean-durationstd)) & (data.duration < (durationmean+durationstd))])
lensd1

lensd1/nobs