Milestone Challenge on Used Bikes Data Set

Welecome to the Milestione Challenge, in this scenario, you will be exploring descriptive statistics on used
bikes dataset .

Note -

 Add extra cells for coding if neccessary.

 Finally restart and run all the cells after the completion of the challenge.

Run the below cell to import the basic neccessary packages

Note- These are basic packages which is needed to solve this challenge,kindly include appropriate modules
from the below given packages to solve this challenge based on the given scenarios.
[1]:

import numpy as np
import pandas as pd
import statistics
import scipy

Run the below cell to download the dataset

[2]:

!wget hrcdn.net/s3_pub/istreet-assets/-ccjO7ToeMlvfSIOr-Wxfg/Used_Bikes.csv
--2021-09-22 10:42:42-- http://hrcdn.net/s3_pub/istreet-assets/-ccjO7ToeMlvfSIOr-Wxfg/Used_Bikes.csv
Resolving hrcdn.net (hrcdn.net)... 23.77.203.146, 23.77.203.144, 2600:1407:1800::173f:49d8, ...
Connecting to hrcdn.net (hrcdn.net)|23.77.203.146|:80... connected.
HTTP request sent, awaiting response... 301 Moved Permanently
Location: https://hrcdn.net/s3_pub/istreet-assets/-ccjO7ToeMlvfSIOr-Wxfg/Used_Bikes.csv [following]
--2021-09-22 10:42:42-- https://hrcdn.net/s3_pub/istreet-assets/-ccjO7ToeMlvfSIOr-Wxfg/Used_Bikes.csv
Connecting to hrcdn.net (hrcdn.net)|23.77.203.146|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 2493547 (2.4M) [application/octet-stream]
Saving to: ‘Used_Bikes.csv’

Used_Bikes.csv 100%[===================>] 2.38M 9.68MB/s in 0.2s

2021-09-22 10:42:43 (9.68 MB/s) - ‘Used_Bikes.csv’ saved [2493547/2493547]

Load the dataset

  Load the Bank Marketing dataset from the file Used_Bikes.csv and save it in the variable df.

[13]:

df = pd.read_csv("Used_Bikes.csv")

Question 1

 (a) From the given above dataset calculate the mean for all numerical columns and convert it into
dictionary and save it in the variable mean.

 (b) From the given above dataset calculate the median for all numerical columns and convert it
into dictionary and save it in the variable median.

 (c) From the given above dataset calculate the mode for all numerical columns and convert it into
dictionary and save it in the variable mode.

 (d) From the mean , median and mode values of the column kms_driven ,it is positively skewed
distribution.

- If the answer for the above statement is yes assign the value yes as string otherwise value no as
string in the variable kms_driven.
Save the outputs for (a), (b) and (c) in the following format -

{Column Name : Value}

Example-

{'age': 85.85,

'kms_driven': 1500.01,

'power': 200.01}

Note- Here round off the mean and median values to two decimal points and mode to the integer.
[57]:

mean = {"price" : price.mean(),"kms_driven" : kms_driven.mean(),"age" :, age.mean(),"power" :,

power.mean()}

print (mean)

median = df.median()
mode = df.mode()

kms_driven = print ('Yes')

File "<ipython-input-57-b3982c389b48>", line 1
mean = {"price" : price.mean(),"kms_driven" : kms_driven.mean(),"age" :, age.mean(),"power" :,
power.mean()}
^
SyntaxError: invalid syntax

Question 2

 (a) From the column owner get the count of all categories and convert it into dictionary and save
it in the variable owner.

 (b) The column owner looks to have a high class imbalance problem.

- If the answer for the above statement is yes assign the value yes as string otherwise value no as
string in the variable class_imb.
For the question (a) save the output in the following format -

{Category Name : Count}

Example-

{'First Owner': 500,

'Fourth Owner Or More': 300,

'Second Owner': 200}

[58]:

owner =

class_imb =
File "<ipython-input-58-7a9c7a6960d5>", line 1
owner =
^
SyntaxError: invalid syntax

Question 3

 For the given dataset find the following -

 - (a) Population Variance of dataset of all numerical columns and save it in variable p_var.

- (b) Population Standard Deviation of dataset of all numerical columns and save it in variable
p_sd.
For the questions (a) and (b) save the output in the following format -
 {Column Name : Value}

Example-

{'age': 85.85,

'kms_driven': 1500.01,

'power': 200.01}

Note- Here round it off the values to two decimal points and convert all variables it into dictionary.
[59]:

p_var =

p_sd =
File "<ipython-input-59-039e0a8010f1>", line 1
p_var =
^
SyntaxError: invalid syntax

Question 4
 For the given dataset find the following -

 - (a) Interquartile Range of the column price and save it in variable iqr_price .

- (b) Interquartile Range of the column kms_driven and save it in variable iqr_kms_driven.
Note- Here round it off the values to two decimal points.
[ ]:

from scipy.stats import iqr

iqr_price =

iqr_kms_driven =

Question 5

 (a) From the given dataset find the correlation matrix for all the numerical columns and save it in
varibale df_corr.Here round it off the values to two decimal points.

 (b) From df_corr Age is negatively correlated with Price.

 - If the answer for the above statement is yes assign the value yes as string otherwise value no as
string in the variable Age_Price.
 (c) From df_corr Power is negatively correlated with Price.

- If the answer for the above statement is yes assign the value yes as string otherwise value no as
string in the variable Power_Price.
For the questions (a) save the output in the following format -

{Column Name : {Column Name : Value}}

Example-

{'age': {'age': 0.2, 'kms_driven': 0.08, 'power': -0.25, 'price': 0.08},

'kms_driven': {'age': -0.15,

'kms_driven': 0.3,

'power': 0.18,

'price': 0.58}}
[ ]:

df_corr =

Age_Price =

Power_Price =

Question 6

 (a) From the given dataset find the skewness for all the numerical columns and save it in
varibale df_skew.Here round it off the values to two decimal points.

 (b) From df_skew age is fairly symmetrical.

- If the answer for the above statement is yes assign the value yes as string otherwise value no as
string in the variable Age_Skew.
 (c) From df_skew power is highly skewed.

- If the answer for the above statement is yes assign the value yes as string otherwise value no as
string in the variable Power_Skew.
For the question (a) save the output in the following format -

{Column Name : Value}

Example-
 {'age': 55.85,

'kms_driven': 76.01,

'power': 61.01}
[ ]:

df_skew =

Age_Skew =

Power_Skew =

Run the below cell to save the results

[ ]:

with open('question1.txt', 'a') as f:

print(mean , file=f)
print(median , file=f)
print(mode , file=f)
print(kms_driven , file=f)

with open('question2.txt', 'a') as f:

print(owner, file=f)
print(class_imb, file=f)

with open('question3.txt', 'a') as f:

print(p_var , file=f)
print(p_sd , file=f)

with open('question4.txt', 'a') as f:

print(iqr_price , file=f)
print(iqr_kms_driven , file=f)

with open('question5.txt', 'a') as f:

print(df_corr , file=f)
print(Age_Price , file=f)
print(Power_Price , file=f)

with open('question6.txt', 'a') as f:

print(df_skew , file=f)
print(Age_Skew , file=f)
 print(Power_Skew , file=f)
[ ]:

 Desc_Stats_Question.ipynb
 Used_Bikes.csv
 score.py
 Terminal 1

import ast

from hashlib import md5

import json

def get_file(file_name):

with open(file_name) as f:

data = f.readlines()

return [s.rstrip('\n') for s in data]

score = 0

try:

#Question1

q1 = 0

question1 = get_file("question1.txt")

question1_1 = ast.literal_eval(question1[0])

question1_1 =sorted(question1_1.items(), key=lambda x: x[0])

question1_2 = ast.literal_eval(question1[1])
 question1_2 =sorted(question1_2.items(), key=lambda x: x[0])

question1_3 = ast.literal_eval(question1[2])

question1_3 =sorted(question1_3.items(), key=lambda x: x[0])

if(md5(str(question1_1).encode()).hexdigest() == "5234e07f99ab2b913f26a9dd0d37a3e7" and

md5(str(question1_2).encode()).hexdigest() == "8cf61882c16304cb93aed577e57073b1" and
md5(str(question1_3).encode()).hexdigest() == "7dfebef1f84a7c27b5562b8e84f692b0" and
md5(str(question1[3]).encode()).hexdigest() == "a6105c0a611b41b08f1209506350279e"):

q1 = q1 +20

except:

q1 = 0

#Question2

try:

q2 = 0

question2 = get_file("question2.txt")

question2_1 = ast.literal_eval(question2[0])

question2_1 =sorted(question2_1.items(), key=lambda x: x[0])

if(md5(str(question2_1).encode()).hexdigest() == "69f10a3346bf0f8d8b902a06642ae4ca" and

md5(str(question2[1]).encode()).hexdigest() == "a6105c0a611b41b08f1209506350279e"):

q2 = q2 + 10

except:

q2 = 0
#Question3

try:

q3 = 0

question3 = get_file("question3.txt")

question3_1 = ast.literal_eval(question3[0])

question3_1 =sorted(question3_1.items(), key=lambda x: x[0])

question3_2 = ast.literal_eval(question3[1])

question3_2 =sorted(question3_2.items(), key=lambda x: x[0])

if(md5(str(question3_1).encode()).hexdigest() == "7759614969fe59a095a56b8eb2f6e812" and

md5(str(question3_2).encode()).hexdigest() == "ba8c0fd84352dd004ac3af7eb5ad13d3"):

q3 = q3 + 20

except:

q3 = 0

#Question4

try:

q4 = 0

question4 = get_file("question4.txt")
 if(md5(str(question4[0]).encode()).hexdigest() == "f19bb046ca4ba9a016360ca151cc8a0a" and
md5(str(question4[1]).encode()).hexdigest() == "3804bd983ddd0d379c3167b9126fc866"):

q4 = q4 +10

except:

q4 = 0

#Question5

try:

q5 = 0

question5 = get_file("question5.txt")

question5_1 = ast.literal_eval(question5[0])

question5_1 =sorted(question5_1.items(), key=lambda x: x[0])

if(md5(json.dumps(question5_1, sort_keys=True).encode('utf-8')).hexdigest() ==
"25fa51b43ce1c5bbc55fa494ce634be1" and md5(str(question5[1]).encode()).hexdigest() ==
"a6105c0a611b41b08f1209506350279e" and md5(str(question5[2]).encode()).hexdigest() ==
"7fa3b767c460b54a2be4d49030b349c7"):

q5 = q5 +20

except:

q5 = 0

#Question6
try:

q6 =0

question6 = get_file("question6.txt")

question6_1 = ast.literal_eval(question6[0])

question6_1 =sorted(question6_1.items(), key=lambda x: x[0])

if(md5(str(question6_1).encode()).hexdigest() == "cf85a8394c75181155a2b67a581601b0" and

md5(str(question6[1]).encode()).hexdigest() == "7fa3b767c460b54a2be4d49030b349c7"):

q6 = q6 +20

except:

q6 = 0

try:

score = q1 + q2 + q3 + q4 + q5 + q6

print("FS_SCORE:{0}%".format(score))

except:

print("FS_SCORE:0%")