import seaborn as sns
import numpy as np
import pandas as pd
from matplotlib import pyplot as plt

data = pd.read_csv("weight-height.csv")
data

# sns.distplot(data["Height"])
sns.boxplot(data["Height"])

<Axes: ylabel='Height'>

min_limit = data["Height"].quantile(0.01)
max_limit = data["Height"].quantile(0.99)

max_limit

74.7857900583366

data

data.describe()

data[(data["Height"]>max_limit) | (data["Height"]<min_limit)]

#Trimming
data1 = data[(data["Height"]<max_limit) & (data["Height"]>min_limit)]
data1

#Capping
new_data = data.copy()
new_data["Height"] = np.where(data["Height"]<min_limit , min_limit , np.where(data["Height"]>max_limit , max_limit , data["Height"]))
new_data

plt.figure(figsize=(16,8))
plt.subplot(2,2,1)
sns.distplot(data["Height"])

plt.subplot(2,2,2)
sns.boxplot(data["Height"])

plt.subplot(2,2,3)
sns.distplot(new_data["Height"])

plt.subplot(2,2,4)
sns.boxplot(new_data["Height"])

plt.show()

C:\Users\Satyam\AppData\Local\Temp\ipykernel_28556\4195842642.py:3: UserWarning: 

`distplot` is a deprecated function and will be removed in seaborn v0.14.0.

Please adapt your code to use either `displot` (a figure-level function with
similar flexibility) or `histplot` (an axes-level function for histograms).

For a guide to updating your code to use the new functions, please see
https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751

  sns.distplot(data["Height"])
C:\Users\Satyam\AppData\Local\Temp\ipykernel_28556\4195842642.py:9: UserWarning: 

`distplot` is a deprecated function and will be removed in seaborn v0.14.0.

Please adapt your code to use either `displot` (a figure-level function with
similar flexibility) or `histplot` (an axes-level function for histograms).

For a guide to updating your code to use the new functions, please see
https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751

  sns.distplot(new_data["Height"])

	Gender	Height	Weight
0	Male	73.847017	241.893563
1	Male	68.781904	162.310473
2	Male	74.110105	212.740856
3	Male	71.730978	220.042470
4	Male	69.881796	206.349801
...	...	...	...
9995	Female	66.172652	136.777454
9996	Female	67.067155	170.867906
9997	Female	63.867992	128.475319
9998	Female	69.034243	163.852461
9999	Female	61.944246	113.649103

	Gender	Height	Weight
0	Male	73.847017	241.893563
1	Male	68.781904	162.310473
2	Male	74.110105	212.740856
3	Male	71.730978	220.042470
4	Male	69.881796	206.349801
...	...	...	...
9995	Female	66.172652	136.777454
9996	Female	67.067155	170.867906
9997	Female	63.867992	128.475319
9998	Female	69.034243	163.852461
9999	Female	61.944246	113.649103

	Height	Weight
count	10000.000000	10000.000000
mean	66.367560	161.440357
std	3.847528	32.108439
min	54.263133	64.700127
25%	63.505620	135.818051
50%	66.318070	161.212928
75%	69.174262	187.169525
max	78.998742	269.989699

	Gender	Height	Weight
23	Male	75.205974	228.761781
190	Male	76.709835	235.035419
197	Male	75.944460	231.924749
202	Male	75.140821	224.124271
215	Male	74.795375	232.635403
...	...	...	...
9761	Female	56.975279	90.341784
9825	Female	55.979198	85.417534
9895	Female	57.740192	93.652957
9904	Female	57.028857	101.202551
9978	Female	57.375759	114.192209

	Gender	Height	Weight
0	Male	73.847017	241.893563
1	Male	68.781904	162.310473
2	Male	74.110105	212.740856
3	Male	71.730978	220.042470
4	Male	69.881796	206.349801
...	...	...	...
9995	Female	66.172652	136.777454
9996	Female	67.067155	170.867906
9997	Female	63.867992	128.475319
9998	Female	69.034243	163.852461
9999	Female	61.944246	113.649103

Capping¶