IMPORT LIBRARIES
In [82]: import pandas as pd
import numpy as np
took dataset from kaggle(csv file)
In [83]: dataset = pd.read_csv(r"C:\Users\khush\Desktop\Salary_Data.csv")
to display the csv file
In [84]: dataset.head()
Out[84]: Age Gender Education Level Job Title Years of Experience Salary
0 32.0 Male Bachelor's Software Engineer 5.0 90000.0
1 28.0 Female Master's Data Analyst 3.0 65000.0
2 45.0 Male PhD Senior Manager 15.0 150000.0
3 36.0 Female Bachelor's Sales Associate 7.0 60000.0
4 52.0 Male Master's Director 20.0 200000.0
removed columns which are not required i.e.
simplified data
In [85]: columns_to_remove = ['Gender', 'Education Level', 'Job Title']
In [86]: dataset = dataset.drop(columns=columns_to_remove)
In [87]: dataset.head()
Out[87]: Age Years of Experience Salary
0 32.0 5.0 90000.0
1 28.0 3.0 65000.0
2 45.0 15.0 150000.0
3 36.0 7.0 60000.0
4 52.0 20.0 200000.0
performed various operation on column
'Age'
In [88]: dataset.Age.mean()
Out[88]: 33.62085944494181
In [89]: dataset.Age.median()
Out[89]: 32.0
In [90]: dataset.Age.mode()
Out[90]: 0 27.0
Name: Age, dtype: float64
In [91]: dataset.Age.max()
Out[91]: 62.0
In [92]: dataset.Age.min()
Out[92]: 21.0
In [93]: column_name = 'Age'
std_dev = dataset[column_name].std()
In [94]: print(f"Standard Deviation for {column_name}: {std_dev}")
Standard Deviation for Age: 7.614632626251171
various operation on column 'salary'
In [95]: dataset.Salary.mean()
Out[95]: 115326.96477086132
In [96]: dataset.Salary.mode()
Out[96]: 0 140000.0
Name: Salary, dtype: float64
In [97]: dataset.Salary.median()
Out[97]: 115000.0
In [98]: dataset.Salary.max()
Out[98]: 250000.0
In [99]: dataset.Salary.min()
Out[99]: 350.0
In [100]: column_name = 'Salary'
std_dev = dataset[column_name].std()
print(f"Standard Deviation for {column_name}: {std_dev}")
Standard Deviation for Salary: 52786.183910682936
operations on entire dataset
In [101]: dataset.mean()
Out[101]: Age 33.620859
Years of Experience 8.094687
Salary 115326.964771
dtype: float64
In [102]: dataset.median()
Out[102]: Age 32.0
Years of Experience 7.0
Salary 115000.0
dtype: float64
In [103]: dataset.min()
Out[103]: Age 21.0
Years of Experience 0.0
Salary 350.0
dtype: float64
In [104]: dataset.max()
Out[104]: Age 62.0
Years of Experience 34.0
Salary 250000.0
dtype: float64
In [105]: dataset.Age.mode()
Out[105]: 0 27.0
Name: Age, dtype: float64
In [106]: dataset.groupby(['Age']).count()
Out[106]: Years of Experience Salary
Age
21.0 18 18
22.0 15 15
23.0 104 104
24.0 240 240
25.0 284 284
26.0 393 393
27.0 517 517
28.0 429 429
29.0 444 444
30.0 449 449
31.0 365 364
32.0 351 351
33.0 398 398
34.0 309 309
35.0 200 200
36.0 282 281
37.0 156 156
38.0 149 149
39.0 158 158
40.0 92 92
41.0 129 129
42.0 176 176
43.0 158 158
44.0 126 126
45.0 144 144
46.0 102 102
47.0 47 47
48.0 98 98
49.0 91 91
50.0 88 88
51.0 30 30
52.0 29 29
53.0 7 7
54.0 68 68
55.0 16 16
Years of Experience Salary
Age
56.0 11 11
57.0 9 9
58.0 7 7
60.0 5 5
61.0 2 2
62.0 5 5
In [107]: dataset.isnull()
Out[107]: Age Years of Experience Salary
0 False False False
1 False False False
2 False False False
3 False False False
4 False False False
... ... ... ...
6699 False False False
6700 False False False
6701 False False False
6702 False False False
6703 False False False
6704 rows × 3 columns
In [108]: std_dev = np.std(dataset)
In [109]: print("standard deviation:", std_dev)
standard deviation: Age 7.614065
Years of Experience 6.058551
Salary 52782.243908
dtype: float64
Box Plot
In [110]: import matplotlib.pyplot as plt
In [111]: dataset = pd.read_csv(r"C:\Users\khush\Desktop\Salary_Data.csv")
In [112]: x = dataset['Age']
y = dataset['Salary']
In [113]: plt.title('Age Salary dataset ')
plt.xlabel('Age')
plt.ylabel('Salary')
plt.bar(x , y)
plt.show()
interquartile range
In [114]: first_quartile = np.percentile(Age, 25)
In [115]: print("25% :",first_quartile)
25% : -0.6727350412768447
In [116]: third_quartile = np.percentile(Age, 75)
In [117]: print("75% :", third_quartile)
75% : 0.6434662147791437
In [118]: first_quartile = np.percentile(Age, 25)
third_quartile = np.percentile(Age, 75)
iqr = third_quartile - first_quartile
In [119]: print("Interquartile Range (IQR):", iqr)
Interquartile Range (IQR): 1.3162012560559884
summary stats function
In [120]: summary_stats = dataset.groupby('Age')['Salary'].describe()
In [121]: print(summary_stats)
count mean std min 25% 50% \
Age
21.0 18.0 25000.000000 0.000000 25000.0 25000.00 25000.0
22.0 15.0 32910.933333 11880.865333 25000.0 25000.00 25000.0
23.0 104.0 47192.009615 18035.442395 579.0 35000.00 50000.0
24.0 240.0 51052.250000 26124.985328 25000.0 25000.00 48132.5
25.0 284.0 63730.387324 28777.491135 550.0 35000.00 60000.0
26.0 393.0 65949.106870 31167.205609 26000.0 45000.00 55000.0
27.0 517.0 77432.729207 33012.912794 30000.0 55000.00 70000.0
28.0 429.0 84140.368298 40685.862170 25000.0 60000.00 70000.0
29.0 444.0 85764.750000 40882.104745 350.0 60000.00 75000.0
30.0 449.0 100903.955457 44141.603325 25000.0 65000.00 95000.0
31.0 364.0 114381.461538 49219.650931 500.0 70000.00 120000.0
32.0 351.0 120500.179487 40343.238208 40000.0 90000.00 120000.0
33.0 398.0 127425.266332 41148.195089 25000.0 100000.00 123520.5
34.0 309.0 132065.291262 38029.021237 50000.0 100000.00 140000.0
35.0 200.0 119365.835000 28282.573449 35000.0 95000.00 120000.0
36.0 281.0 134071.725979 35196.096365 35000.0 100000.00 139413.0
37.0 156.0 146939.461538 32923.368331 75000.0 115000.00 150000.0
38.0 149.0 138185.570470 30591.206601 80000.0 119000.00 136449.0
39.0 158.0 147282.715190 37107.978657 55000.0 120000.00 145000.0
40.0 92.0 149862.989130 38457.087535 60000.0 122000.00 150000.0
41.0 129.0 155235.565891 32816.117854 80000.0 131000.00 151315.0
42.0 176.0 155952.477273 23802.443693 100000.0 139571.50 170000.0
43.0 158.0 165409.398734 19730.539525 105000.0 150000.00 162000.0
44.0 126.0 160518.873016 18377.397914 110000.0 150000.00 162037.5
45.0 144.0 170334.291667 26086.731136 80000.0 150000.00 180000.0
46.0 102.0 171242.362745 16885.301897 120000.0 160000.00 180000.0
47.0 47.0 178750.106383 11582.239177 135000.0 170000.00 178859.0
48.0 98.0 192723.846939 16884.955629 140000.0 180255.25 190000.0
49.0 91.0 189013.582418 18146.688329 120177.0 182392.00 185000.0
50.0 88.0 190849.897727 18832.132979 130000.0 180000.00 190000.0
51.0 30.0 200356.066667 27080.013909 130000.0 190000.00 190000.0
52.0 29.0 187629.379310 15720.313915 161568.0 185462.00 186963.0
53.0 7.0 180806.571429 11812.715266 166109.0 173054.50 181714.0
54.0 68.0 189816.250000 8875.741981 158254.0 190000.00 192103.5
55.0 16.0 198482.187500 10884.112294 183020.0 190407.25 193964.0
56.0 11.0 196577.636364 4507.360808 195000.0 195000.00 195000.0
57.0 9.0 176993.777778 31698.597168 121450.0 188232.00 191790.0
58.0 7.0 195715.428571 4496.983539 190004.0 192502.00 195000.0
60.0 5.0 186132.400000 6855.522467 179180.0 179180.00 188651.0
61.0 2.0 200000.000000 0.000000 200000.0 200000.00 200000.0
62.0 5.0 200000.000000 0.000000 200000.0 200000.00 200000.0
75% max
Age
21.0 25000.0 25000.0
22.0 45000.0 51832.0
23.0 52807.0 119836.0
24.0 60000.0 125000.0
25.0 90000.0 169159.0
26.0 85000.0 135000.0
27.0 80000.0 180000.0
28.0 110000.0 175000.0
29.0 95000.0 182000.0
30.0 120000.0 190000.0
31.0 140000.0 195000.0
32.0 145000.0 195000.0
33.0 148000.0 198000.0
34.0 160976.0 196000.0
35.0 140000.0 190000.0
36.0 160000.0 185000.0
37.0 170000.0 195000.0
38.0 155000.0 195000.0
39.0 170000.0 210000.0
40.0 160000.0 215000.0
41.0 185000.0 200000.0
42.0 180000.0 197000.0
43.0 185000.0 198000.0
44.0 170000.0 220000.0
45.0 185000.0 250000.0
46.0 180000.0 220000.0
47.0 190000.0 200000.0
48.0 210000.0 219000.0
49.0 195000.0 228000.0
50.0 200000.0 250000.0
51.0 230000.0 240000.0
52.0 190596.0 250000.0
53.0 188357.0 195000.0
54.0 195000.0 195270.0
55.0 210000.0 210000.0
56.0 195000.0 210000.0
57.0 195000.0 200000.0
58.0 200000.0 200000.0
60.0 188651.0 195000.0
61.0 200000.0 200000.0
62.0 200000.0 200000.0
In [ ]:
