ytshih/statistics2023-final
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Done analyzing

Browse Source
This commit is contained in:
Ian Shih
2023-06-15 12:33:33 +08:00
parent c746cdd016
commit 0e4280a1ae
15 changed files with 151 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

68
descriptive-analysis.py
View File

@@ -1,15 +1,69 @@
import pandas as pd
import seaborn as sns
from matplotlib import pyplot
from matplotlib import pyplot as plt
data = pd.read_csv("result.csv")
individual = data.loc[data['isOffice'] == 0]
data['viewRate'] = (data['view'] / data['video']) / data['fan']
ind = data.loc[data['isOffice'] == 0]
office = data.loc[data['isOffice'] == 1]
print(individual['fan'])
print(office['fan'])
# Question 1
sns.histplot(data=ind, x='fan', bins=100)
plt.savefig("q1-ind-fan-hist.png"); plt.show()
print(list(individual['fan']))
pyplot.hist(list(individual['fan']))
pyplot.show()
sns.histplot(data=office, x='fan', bins=100)
plt.savefig("q1-office-fan-hist.png"); plt.show()
sns.boxplot(data=[ind['fan'], office['fan']], orient='h')
plt.savefig("q1-fan-box.png"); plt.show()
# Question 2
ind = ind.sort_values(
by=['viewRate']
).iloc[
len(ind.index)*5//100:len(ind.index)*95//100
]
office = office.sort_values(
by=['viewRate']
).iloc[
len(office.index)*5//100:len(office.index)*95//100
]
sns.histplot(data=ind, x='viewRate', bins=100)
plt.savefig("q2-ind-viewRate-hist.png"); plt.show()
sns.histplot(data=office, x='viewRate', bins=100)
plt.savefig("q2-office-viewRate-hist.png"); plt.show()
sns.boxplot(data=[ind['viewRate'], office['viewRate']], orient='h')
plt.savefig("q2-viewRate-box.png"); plt.show()
# Question 3
firstHalf = data.iloc[lambda x: x.index < len(data.index)//2]
firstHalf = firstHalf.sort_values(
by=['viewRate']
).iloc[
len(firstHalf.index)*5//100:len(firstHalf.index)*95//100
]
secondHalf = data.iloc[lambda x: x.index >= len(data.index)//2]
secondHalf = secondHalf.sort_values(
by=['viewRate']
).iloc[
len(secondHalf.index)*5//100:len(secondHalf.index)*95//100
]
sns.histplot(data=firstHalf, x='viewRate', bins=100)
plt.savefig("q3-firstHalf-viewRate-hist.png"); plt.show()
sns.histplot(data=secondHalf, x='viewRate', bins=100)
plt.savefig("q3-secondHalf-viewRate-hist.png"); plt.show()
sns.boxplot(
data=[firstHalf['viewRate'], secondHalf['viewRate']],
orient='h'
)
plt.savefig("q3-viewRate-box.png"); plt.show()