agabka/projekt-checkpoint.ipynb at 6bdf024137770c1dc21a976c5346d433ff17f271

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

dane = pd.read_csv(r'C:\Users\HP\Desktop\podyplomówka\cancer_patient_data_sets.csv', index_col = 0)
dane.head()

	Patient Id	Age	Gender	Air Pollution	Alcohol use	Dust Allergy	OccuPational Hazards	Genetic Risk	chronic Lung Disease	Balanced Diet	...	Fatigue	Weight Loss	Shortness of Breath	Wheezing	Swallowing Difficulty	Clubbing of Finger Nails	Frequent Cold	Dry Cough	Snoring	Level
index
0	P1	33	1	2	4	5	4	3	2	2	...	3	4	2	2	3	1	2	3	4	Low
1	P10	17	1	3	1	5	3	4	2	2	...	1	3	7	8	6	2	1	7	2	Medium
2	P100	35	1	4	5	6	5	5	4	6	...	8	7	9	2	1	4	6	7	2	High
3	P1000	37	1	7	7	7	7	6	7	7	...	4	2	3	1	4	5	6	7	5	High
4	P101	46	1	6	8	7	7	7	6	7	...	3	2	4	1	4	2	4	2	3	High

5 rows × 25 columns

dane.info()

<class 'pandas.core.frame.DataFrame'>
Index: 1000 entries, 0 to 999
Data columns (total 25 columns):
 #   Column                    Non-Null Count  Dtype 
---  ------                    --------------  ----- 
 0   Patient Id                1000 non-null   object
 1   Age                       1000 non-null   int64 
 2   Gender                    1000 non-null   int64 
 3   Air Pollution             1000 non-null   int64 
 4   Alcohol use               1000 non-null   int64 
 5   Dust Allergy              1000 non-null   int64 
 6   OccuPational Hazards      1000 non-null   int64 
 7   Genetic Risk              1000 non-null   int64 
 8   chronic Lung Disease      1000 non-null   int64 
 9   Balanced Diet             1000 non-null   int64 
 10  Obesity                   1000 non-null   int64 
 11  Smoking                   1000 non-null   int64 
 12  Passive Smoker            1000 non-null   int64 
 13  Chest Pain                1000 non-null   int64 
 14  Coughing of Blood         1000 non-null   int64 
 15  Fatigue                   1000 non-null   int64 
 16  Weight Loss               1000 non-null   int64 
 17  Shortness of Breath       1000 non-null   int64 
 18  Wheezing                  1000 non-null   int64 
 19  Swallowing Difficulty     1000 non-null   int64 
 20  Clubbing of Finger Nails  1000 non-null   int64 
 21  Frequent Cold             1000 non-null   int64 
 22  Dry Cough                 1000 non-null   int64 
 23  Snoring                   1000 non-null   int64 
 24  Level                     1000 non-null   object
dtypes: int64(23), object(2)
memory usage: 203.1+ KB

dane.describe().T

	count	mean	std	min	25%	50%	75%	max
Age	1000.0	37.174	12.005493	14.0	27.75	36.0	45.0	73.0
Gender	1000.0	1.402	0.490547	1.0	1.00	1.0	2.0	2.0
Air Pollution	1000.0	3.840	2.030400	1.0	2.00	3.0	6.0	8.0
Alcohol use	1000.0	4.563	2.620477	1.0	2.00	5.0	7.0	8.0
Dust Allergy	1000.0	5.165	1.980833	1.0	4.00	6.0	7.0	8.0
OccuPational Hazards	1000.0	4.840	2.107805	1.0	3.00	5.0	7.0	8.0
Genetic Risk	1000.0	4.580	2.126999	1.0	2.00	5.0	7.0	7.0
chronic Lung Disease	1000.0	4.380	1.848518	1.0	3.00	4.0	6.0	7.0
Balanced Diet	1000.0	4.491	2.135528	1.0	2.00	4.0	7.0	7.0
Obesity	1000.0	4.465	2.124921	1.0	3.00	4.0	7.0	7.0
Smoking	1000.0	3.948	2.495902	1.0	2.00	3.0	7.0	8.0
Passive Smoker	1000.0	4.195	2.311778	1.0	2.00	4.0	7.0	8.0
Chest Pain	1000.0	4.438	2.280209	1.0	2.00	4.0	7.0	9.0
Coughing of Blood	1000.0	4.859	2.427965	1.0	3.00	4.0	7.0	9.0
Fatigue	1000.0	3.856	2.244616	1.0	2.00	3.0	5.0	9.0
Weight Loss	1000.0	3.855	2.206546	1.0	2.00	3.0	6.0	8.0
Shortness of Breath	1000.0	4.240	2.285087	1.0	2.00	4.0	6.0	9.0
Wheezing	1000.0	3.777	2.041921	1.0	2.00	4.0	5.0	8.0
Swallowing Difficulty	1000.0	3.746	2.270383	1.0	2.00	4.0	5.0	8.0
Clubbing of Finger Nails	1000.0	3.923	2.388048	1.0	2.00	4.0	5.0	9.0
Frequent Cold	1000.0	3.536	1.832502	1.0	2.00	3.0	5.0	7.0
Dry Cough	1000.0	3.853	2.039007	1.0	2.00	4.0	6.0	7.0
Snoring	1000.0	2.926	1.474686	1.0	2.00	3.0	4.0	7.0

dane.columns

Index(['Patient Id', 'Age', 'Gender', 'Air Pollution', 'Alcohol use',
       'Dust Allergy', 'OccuPational Hazards', 'Genetic Risk',
       'chronic Lung Disease', 'Balanced Diet', 'Obesity', 'Smoking',
       'Passive Smoker', 'Chest Pain', 'Coughing of Blood', 'Fatigue',
       'Weight Loss', 'Shortness of Breath', 'Wheezing',
       'Swallowing Difficulty', 'Clubbing of Finger Nails', 'Frequent Cold',
       'Dry Cough', 'Snoring', 'Level'],
      dtype='object')

dane2 = dane.groupby('Gender').size()
dane2

Gender
1    598
2    402
dtype: int64


dane['Gender'].value_counts().plot(kind = 'bar')

<Axes: xlabel='Gender'>

dane3 = [dane.groupby('Smoking').size()]
dane3

[Smoking
 1    181
 2    222
 3    172
 4     59
 5     10
 6     60
 7    207
 8     89
 dtype: int64]

dane['Smoking'].value_counts().plot(kind = 'pie')

<Axes: ylabel='count'>

dane4 = [dane.groupby('Passive Smoker').size()]
dane4

[Passive Smoker
 1     60
 2    284
 3    140
 4    161
 5     30
 6     30
 7    187
 8    108
 dtype: int64]

dane['Passive Smoker'].value_counts().plot(kind = 'pie')

<Axes: ylabel='count'>

dane.groupby(['Smoking','Gender']).size()

Smoking  Gender
1        1         102
         2          79
2        1         102
         2         120
3        1          79
         2          93
4        1          49
         2          10
5        1          10
6        1          28
         2          32
7        1         167
         2          40
8        1          61
         2          28
dtype: int64

dane6 = dane.groupby(['Smoking','Gender'])
dane6[['Smoking', 'Gender']].value_counts().plot(kind = 'bar')

<Axes: xlabel='Smoking,Gender'>

dane7 = dane['Air Pollution'].value_counts()
dane7.sort_values()

Air Pollution
8     19
5     20
7     30
4     90
1    141
3    173
2    201
6    326
Name: count, dtype: int64

dane7 = dane['Air Pollution'].value_counts().plot(kind = 'bar')
dane7

<Axes: xlabel='Air Pollution'>

121 KiB Raw Blame History Unescape Escape

121 KiB

Raw Blame History