 # Untitled

Apr 13th, 2021 (edited)
470
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
1. # data analysis workshop 1, 13.4.2021
2.
3. # example, car sales
4.
5. import numpy as np
6. import pandas as pd
7. import seaborn as sns
8. import matplotlib.pyplot as plt
9. from scipy import stats
10.
11. def percentage_difference(row):
12.     selling = row['Selling_Price']
14.     result = 1 - round(selling / road, 2)
15.     return result
16.
17.
19.
20. cars = cars.drop('Car_Name', axis=1)
21.
22. cars['Price_Difference'] = cars.apply(percentage_difference, axis=1)
23.
24. column_names = ['Year', 'Selling_Price', 'Present_Price', 'Price_Difference', 'Kms_Driven', 'Fuel_Type', 'Seller_Type', 'Transmission', 'Owner']
25. cars = cars.reindex(columns=column_names)
26.
27. cars = cars.drop('Owner', axis=1)
28.
29. automatic_diesels = cars[cars['Fuel_Type'] == 'Diesel']
30.
31. # the amount of extra costs (price difference) is affected by car year and kms driven
32. correlations = cars.corr()
33.
34. plt.clf()
35. sns.pairplot(cars)
36. plt.figure()
37.
38.
39. # Automatic transmission cars tend to be more expensive
40. plt.clf()
41. sns.pairplot(cars, hue='Transmission')
42. plt.figure()
43.
44. # Also Diesel fuel type seem to be more valuable in used cars
45. plt.clf()
46. sns.pairplot(cars, hue='Fuel_Type')
47. plt.figure()
48.
49. plt.clf()
50. sns.boxplot(x='Transmission', y='Present_Price', data=cars, hue='Fuel_Type')
51. plt.figure()
52.
53.
RAW Paste Data