[seaborn]S6_02_pairplot,displot,heatmap(correlations)

cancer.csv

0.12MB

 

 

 

Seaborn

https://seaborn.pydata.org/examples/index.html

 

 

●pandas: data manipulation using dataframes
●numpy: data statistical analysis
●matplotlib: data visualisation
●seaborn: Statistical data visualization

 

 

https://www.kaggle.com/datasets/yasserh/breast-cancer-dataset?resource=download

 

In [58]:

# Seaborn offers enhanced features compared to matplotlib

# import libraries 
import pandas as pd 
import numpy as np 
import matplotlib.pyplot as plt
import seaborn as sns

 

In [60]:

cancer_df = pd.read_csv('cancer.csv'); cancer_df

 

Out[60]:

	id	diagnosis	radius_mean	texture_mean	perimeter_mean	area_mean	smoothness_mean	compactness_mean	concavity_mean	concave points_mean	...	radius_worst	texture_worst	perimeter_worst	area_worst	smoothness_worst	compactness_worst	concavity_worst	concave points_worst	symmetry_worst	fractal_dimension_worst
0	842302	M	17.99	10.38	122.80	1001.0	0.11840	0.27760	0.30010	0.14710	...	25.380	17.33	184.60	2019.0	0.16220	0.66560	0.7119	0.2654	0.4601	0.11890
1	842517	M	20.57	17.77	132.90	1326.0	0.08474	0.07864	0.08690	0.07017	...	24.990	23.41	158.80	1956.0	0.12380	0.18660	0.2416	0.1860	0.2750	0.08902
2	84300903	M	19.69	21.25	130.00	1203.0	0.10960	0.15990	0.19740	0.12790	...	23.570	25.53	152.50	1709.0	0.14440	0.42450	0.4504	0.2430	0.3613	0.08758
3	84348301	M	11.42	20.38	77.58	386.1	0.14250	0.28390	0.24140	0.10520	...	14.910	26.50	98.87	567.7	0.20980	0.86630	0.6869	0.2575	0.6638	0.17300
4	84358402	M	20.29	14.34	135.10	1297.0	0.10030	0.13280	0.19800	0.10430	...	22.540	16.67	152.20	1575.0	0.13740	0.20500	0.4000	0.1625	0.2364	0.07678
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
564	926424	M	21.56	22.39	142.00	1479.0	0.11100	0.11590	0.24390	0.13890	...	25.450	26.40	166.10	2027.0	0.14100	0.21130	0.4107	0.2216	0.2060	0.07115
565	926682	M	20.13	28.25	131.20	1261.0	0.09780	0.10340	0.14400	0.09791	...	23.690	38.25	155.00	1731.0	0.11660	0.19220	0.3215	0.1628	0.2572	0.06637
566	926954	M	16.60	28.08	108.30	858.1	0.08455	0.10230	0.09251	0.05302	...	18.980	34.12	126.70	1124.0	0.11390	0.30940	0.3403	0.1418	0.2218	0.07820
567	927241	M	20.60	29.33	140.10	1265.0	0.11780	0.27700	0.35140	0.15200	...	25.740	39.42	184.60	1821.0	0.16500	0.86810	0.9387	0.2650	0.4087	0.12400
568	92751	B	7.76	24.54	47.92	181.0	0.05263	0.04362	0.00000	0.00000	...	9.456	30.37	59.16	268.6	0.08996	0.06444	0.0000	0.0000	0.2871	0.07039

569 rows × 32 columns

 

In [62]:

def func_diag(row):
  if 'M' in row:
    return 1
  else:
    return 0
cancer_df['diagnosis'] = cancer_df['diagnosis'].apply(func_diag)
cancer_df.head()

 

Out[62]:

	id	diagnosis	radius_mean	texture_mean	perimeter_mean	area_mean	smoothness_mean	compactness_mean	concavity_mean	concave points_mean	...	radius_worst	texture_worst	perimeter_worst	area_worst	smoothness_worst	compactness_worst	concavity_worst	concave points_worst	symmetry_worst	fractal_dimension_worst
0	842302	1	17.99	10.38	122.80	1001.0	0.11840	0.27760	0.3001	0.14710	...	25.38	17.33	184.60	2019.0	0.1622	0.6656	0.7119	0.2654	0.4601	0.11890
1	842517	1	20.57	17.77	132.90	1326.0	0.08474	0.07864	0.0869	0.07017	...	24.99	23.41	158.80	1956.0	0.1238	0.1866	0.2416	0.1860	0.2750	0.08902
2	84300903	1	19.69	21.25	130.00	1203.0	0.10960	0.15990	0.1974	0.12790	...	23.57	25.53	152.50	1709.0	0.1444	0.4245	0.4504	0.2430	0.3613	0.08758
3	84348301	1	11.42	20.38	77.58	386.1	0.14250	0.28390	0.2414	0.10520	...	14.91	26.50	98.87	567.7	0.2098	0.8663	0.6869	0.2575	0.6638	0.17300
4	84358402	1	20.29	14.34	135.10	1297.0	0.10030	0.13280	0.1980	0.10430	...	22.54	16.67	152.20	1575.0	0.1374	0.2050	0.4000	0.1625	0.2364	0.07678

5 rows × 32 columns

 

 

pairplot

 

In [70]:

# pairplot
# vars에 변수를 제한시킨다.
sns.pairplot(cancer_df,hue='diagnosis', vars = ['radius_mean','texture_mean','area_mean','perimeter_mean','smoothness_mean'] )

 

Out[70]:

<seaborn.axisgrid.PairGrid at 0x7f8a114c1a00>

 

 

 

heatmap

 

In [71]:

# correlations
sns.heatmap(cancer_df.corr())

 

Out[71]:

<matplotlib.axes._subplots.AxesSubplot at 0x7f8a0d399730>

 

 

In [76]:

plt.figure(figsize = (20,10))
sns.heatmap(cancer_df.corr(), annot = True)

 

Out[76]:

<matplotlib.axes._subplots.AxesSubplot at 0x7f8a0ca911c0>

 

 

 

distplot

 

In [78]:

# distribution : distplot
# Displot combines matplotlib histogram function with kdeplot()
# KDE : Kernel Density Estimate
# KDE is used to plot the Probability Density of a continuous variable (연속 변량의 확률밀도)
sns.distplot(cancer_df['radius_mean'],bins=5, color = 'r')

 

 

/usr/local/lib/python3.8/dist-packages/seaborn/distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)

Out[78]:

<matplotlib.axes._subplots.AxesSubplot at 0x7f8a0c341400>

 

 

In [79]:

class_0 = cancer_df[ cancer_df['diagnosis'] == 0 ]
class_1 = cancer_df[ cancer_df['diagnosis'] == 1 ]

 

In [81]:

plt.figure(figsize = (10,8))
sns.distplot(class_0['radius_mean'], bins= 15, color = 'r')
sns.distplot(class_1['radius_mean'], bins= 15, color = 'g')

 

 

/usr/local/lib/python3.8/dist-packages/seaborn/distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)
/usr/local/lib/python3.8/dist-packages/seaborn/distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)

Out[81]:

<matplotlib.axes._subplots.AxesSubplot at 0x7f8a0c2d2400>