In [26]:
# import libraries
import pandas as pd # Import Pandas for data manipulation using dataframes
import numpy as np # Import Numpy for data statistical analysis
import matplotlib.pyplot as plt # Import matplotlib for data visualisation
import seaborn as sb # Statistical data visualization
# %matplotlib inline
In [2]:
from sklearn.datasets import load_breast_cancer
In [4]:
cancer = load_breast_cancer()
In [5]:
cancer
Out[5]:
{'data': array([[1.799e+01, 1.038e+01, 1.228e+02, ..., 2.654e-01, 4.601e-01,
1.189e-01],
[2.057e+01, 1.777e+01, 1.329e+02, ..., 1.860e-01, 2.750e-01,
8.902e-02],
[1.969e+01, 2.125e+01, 1.300e+02, ..., 2.430e-01, 3.613e-01,
8.758e-02],
...,
[1.660e+01, 2.808e+01, 1.083e+02, ..., 1.418e-01, 2.218e-01,
7.820e-02],
[2.060e+01, 2.933e+01, 1.401e+02, ..., 2.650e-01, 4.087e-01,
1.240e-01],
[7.760e+00, 2.454e+01, 4.792e+01, ..., 0.000e+00, 2.871e-01,
7.039e-02]]),
'target': array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0,
0, 0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 0, 1, 1, 1, 1, 0, 1, 0, 0,
1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 0, 0,
1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 0, 1,
1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 1, 0,
0, 1, 0, 0, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1,
1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 0, 1, 1, 1,
1, 0, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 0, 0,
0, 0, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0,
1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, 0, 0, 1, 0, 1, 1,
1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 0, 1, 0, 0, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0,
0, 1, 1, 1, 1, 0, 1, 0, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0,
0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0,
1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1,
1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 0,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 1, 1, 1,
1, 0, 1, 1, 0, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0,
1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1,
1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 0, 1, 1,
1, 1, 1, 0, 1, 1, 0, 1, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1]),
'frame': None,
'target_names': array(['malignant', 'benign'], dtype='<U9'),
'DESCR': '.. _breast_cancer_dataset:\n\nBreast cancer wisconsin (diagnostic) dataset\n--------------------------------------------\n\n**Data Set Characteristics:**\n\n :Number of Instances: 569\n\n :Number of Attributes: 30 numeric, predictive attributes and the class\n\n :Attribute Information:\n - radius (mean of distances from center to points on the perimeter)\n - texture (standard deviation of gray-scale values)\n - perimeter\n - area\n - smoothness (local variation in radius lengths)\n - compactness (perimeter^2 / area - 1.0)\n - concavity (severity of concave portions of the contour)\n - concave points (number of concave portions of the contour)\n - symmetry\n - fractal dimension ("coastline approximation" - 1)\n\n The mean, standard error, and "worst" or largest (mean of the three\n worst/largest values) of these features were computed for each image,\n resulting in 30 features. For instance, field 0 is Mean Radius, field\n 10 is Radius SE, field 20 is Worst Radius.\n\n - class:\n - WDBC-Malignant\n - WDBC-Benign\n\n :Summary Statistics:\n\n ===================================== ====== ======\n Min Max\n ===================================== ====== ======\n radius (mean): 6.981 28.11\n texture (mean): 9.71 39.28\n perimeter (mean): 43.79 188.5\n area (mean): 143.5 2501.0\n smoothness (mean): 0.053 0.163\n compactness (mean): 0.019 0.345\n concavity (mean): 0.0 0.427\n concave points (mean): 0.0 0.201\n symmetry (mean): 0.106 0.304\n fractal dimension (mean): 0.05 0.097\n radius (standard error): 0.112 2.873\n texture (standard error): 0.36 4.885\n perimeter (standard error): 0.757 21.98\n area (standard error): 6.802 542.2\n smoothness (standard error): 0.002 0.031\n compactness (standard error): 0.002 0.135\n concavity (standard error): 0.0 0.396\n concave points (standard error): 0.0 0.053\n symmetry (standard error): 0.008 0.079\n fractal dimension (standard error): 0.001 0.03\n radius (worst): 7.93 36.04\n texture (worst): 12.02 49.54\n perimeter (worst): 50.41 251.2\n area (worst): 185.2 4254.0\n smoothness (worst): 0.071 0.223\n compactness (worst): 0.027 1.058\n concavity (worst): 0.0 1.252\n concave points (worst): 0.0 0.291\n symmetry (worst): 0.156 0.664\n fractal dimension (worst): 0.055 0.208\n ===================================== ====== ======\n\n :Missing Attribute Values: None\n\n :Class Distribution: 212 - Malignant, 357 - Benign\n\n :Creator: Dr. William H. Wolberg, W. Nick Street, Olvi L. Mangasarian\n\n :Donor: Nick Street\n\n :Date: November, 1995\n\nThis is a copy of UCI ML Breast Cancer Wisconsin (Diagnostic) datasets.\nhttps://goo.gl/U2Uwz2\n\nFeatures are computed from a digitized image of a fine needle\naspirate (FNA) of a breast mass. They describe\ncharacteristics of the cell nuclei present in the image.\n\nSeparating plane described above was obtained using\nMultisurface Method-Tree (MSM-T) [K. P. Bennett, "Decision Tree\nConstruction Via Linear Programming." Proceedings of the 4th\nMidwest Artificial Intelligence and Cognitive Science Society,\npp. 97-101, 1992], a classification method which uses linear\nprogramming to construct a decision tree. Relevant features\nwere selected using an exhaustive search in the space of 1-4\nfeatures and 1-3 separating planes.\n\nThe actual linear program used to obtain the separating plane\nin the 3-dimensional space is that described in:\n[K. P. Bennett and O. L. Mangasarian: "Robust Linear\nProgramming Discrimination of Two Linearly Inseparable Sets",\nOptimization Methods and Software 1, 1992, 23-34].\n\nThis database is also available through the UW CS ftp server:\n\nftp ftp.cs.wisc.edu\ncd math-prog/cpo-dataset/machine-learn/WDBC/\n\n.. topic:: References\n\n - W.N. Street, W.H. Wolberg and O.L. Mangasarian. Nuclear feature extraction \n for breast tumor diagnosis. IS&T/SPIE 1993 International Symposium on \n Electronic Imaging: Science and Technology, volume 1905, pages 861-870,\n San Jose, CA, 1993.\n - O.L. Mangasarian, W.N. Street and W.H. Wolberg. Breast cancer diagnosis and \n prognosis via linear programming. Operations Research, 43(4), pages 570-577, \n July-August 1995.\n - W.H. Wolberg, W.N. Street, and O.L. Mangasarian. Machine learning techniques\n to diagnose breast cancer from fine-needle aspirates. Cancer Letters 77 (1994) \n 163-171.',
'feature_names': array(['mean radius', 'mean texture', 'mean perimeter', 'mean area',
'mean smoothness', 'mean compactness', 'mean concavity',
'mean concave points', 'mean symmetry', 'mean fractal dimension',
'radius error', 'texture error', 'perimeter error', 'area error',
'smoothness error', 'compactness error', 'concavity error',
'concave points error', 'symmetry error',
'fractal dimension error', 'worst radius', 'worst texture',
'worst perimeter', 'worst area', 'worst smoothness',
'worst compactness', 'worst concavity', 'worst concave points',
'worst symmetry', 'worst fractal dimension'], dtype='<U23'),
'filename': 'breast_cancer.csv',
'data_module': 'sklearn.datasets.data'}
In [6]:
cancer.keys()
Out[6]:
dict_keys(['data', 'target', 'frame', 'target_names', 'DESCR', 'feature_names', 'filename', 'data_module'])
In [13]:
print(cancer['feature_names'])
['mean radius' 'mean texture' 'mean perimeter' 'mean area' 'mean smoothness' 'mean compactness' 'mean concavity' 'mean concave points' 'mean symmetry' 'mean fractal dimension' 'radius error' 'texture error' 'perimeter error' 'area error' 'smoothness error' 'compactness error' 'concavity error' 'concave points error' 'symmetry error' 'fractal dimension error' 'worst radius' 'worst texture' 'worst perimeter' 'worst area' 'worst smoothness' 'worst compactness' 'worst concavity' 'worst concave points' 'worst symmetry' 'worst fractal dimension']
In [ ]:
In [ ]:
# np.c_ 와 np.append
In [15]:
col_names=np.append(cancer['feature_names'], 'target' ) # 타겟이라는 컬럼을 추가하라.
In [16]:
col_names
Out[16]:
array(['mean radius', 'mean texture', 'mean perimeter', 'mean area',
'mean smoothness', 'mean compactness', 'mean concavity',
'mean concave points', 'mean symmetry', 'mean fractal dimension',
'radius error', 'texture error', 'perimeter error', 'area error',
'smoothness error', 'compactness error', 'concavity error',
'concave points error', 'symmetry error',
'fractal dimension error', 'worst radius', 'worst texture',
'worst perimeter', 'worst area', 'worst smoothness',
'worst compactness', 'worst concavity', 'worst concave points',
'worst symmetry', 'worst fractal dimension', 'target'],
dtype='<U23')
In [18]:
cancer_data = np.c_[ cancer['data'] , cancer[ 'target']] # data 데이터 프레임에 target 컬럼의 값을 더하라
In [20]:
df = pd.DataFrame(data=cancer_data, columns= col_names)
In [25]:
df
Out[25]:
| mean radius | mean texture | mean perimeter | mean area | mean smoothness | mean compactness | mean concavity | mean concave points | mean symmetry | mean fractal dimension | ... | worst texture | worst perimeter | worst area | worst smoothness | worst compactness | worst concavity | worst concave points | worst symmetry | worst fractal dimension | target | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 17.99 | 10.38 | 122.80 | 1001.0 | 0.11840 | 0.27760 | 0.30010 | 0.14710 | 0.2419 | 0.07871 | ... | 17.33 | 184.60 | 2019.0 | 0.16220 | 0.66560 | 0.7119 | 0.2654 | 0.4601 | 0.11890 | 0.0 |
| 1 | 20.57 | 17.77 | 132.90 | 1326.0 | 0.08474 | 0.07864 | 0.08690 | 0.07017 | 0.1812 | 0.05667 | ... | 23.41 | 158.80 | 1956.0 | 0.12380 | 0.18660 | 0.2416 | 0.1860 | 0.2750 | 0.08902 | 0.0 |
| 2 | 19.69 | 21.25 | 130.00 | 1203.0 | 0.10960 | 0.15990 | 0.19740 | 0.12790 | 0.2069 | 0.05999 | ... | 25.53 | 152.50 | 1709.0 | 0.14440 | 0.42450 | 0.4504 | 0.2430 | 0.3613 | 0.08758 | 0.0 |
| 3 | 11.42 | 20.38 | 77.58 | 386.1 | 0.14250 | 0.28390 | 0.24140 | 0.10520 | 0.2597 | 0.09744 | ... | 26.50 | 98.87 | 567.7 | 0.20980 | 0.86630 | 0.6869 | 0.2575 | 0.6638 | 0.17300 | 0.0 |
| 4 | 20.29 | 14.34 | 135.10 | 1297.0 | 0.10030 | 0.13280 | 0.19800 | 0.10430 | 0.1809 | 0.05883 | ... | 16.67 | 152.20 | 1575.0 | 0.13740 | 0.20500 | 0.4000 | 0.1625 | 0.2364 | 0.07678 | 0.0 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 564 | 21.56 | 22.39 | 142.00 | 1479.0 | 0.11100 | 0.11590 | 0.24390 | 0.13890 | 0.1726 | 0.05623 | ... | 26.40 | 166.10 | 2027.0 | 0.14100 | 0.21130 | 0.4107 | 0.2216 | 0.2060 | 0.07115 | 0.0 |
| 565 | 20.13 | 28.25 | 131.20 | 1261.0 | 0.09780 | 0.10340 | 0.14400 | 0.09791 | 0.1752 | 0.05533 | ... | 38.25 | 155.00 | 1731.0 | 0.11660 | 0.19220 | 0.3215 | 0.1628 | 0.2572 | 0.06637 | 0.0 |
| 566 | 16.60 | 28.08 | 108.30 | 858.1 | 0.08455 | 0.10230 | 0.09251 | 0.05302 | 0.1590 | 0.05648 | ... | 34.12 | 126.70 | 1124.0 | 0.11390 | 0.30940 | 0.3403 | 0.1418 | 0.2218 | 0.07820 | 0.0 |
| 567 | 20.60 | 29.33 | 140.10 | 1265.0 | 0.11780 | 0.27700 | 0.35140 | 0.15200 | 0.2397 | 0.07016 | ... | 39.42 | 184.60 | 1821.0 | 0.16500 | 0.86810 | 0.9387 | 0.2650 | 0.4087 | 0.12400 | 0.0 |
| 568 | 7.76 | 24.54 | 47.92 | 181.0 | 0.05263 | 0.04362 | 0.00000 | 0.00000 | 0.1587 | 0.05884 | ... | 30.37 | 59.16 | 268.6 | 0.08996 | 0.06444 | 0.0000 | 0.0000 | 0.2871 | 0.07039 | 1.0 |
569 rows × 31 columns
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
STEP #3: VISUALIZING THE DATA¶
In [ ]:
# pairplot 을 이용해서, 각 컬럼의 관계를 파악하세요
# 상관계수도 보여주세요
In [28]:
df.columns
Out[28]:
Index(['mean radius', 'mean texture', 'mean perimeter', 'mean area',
'mean smoothness', 'mean compactness', 'mean concavity',
'mean concave points', 'mean symmetry', 'mean fractal dimension',
'radius error', 'texture error', 'perimeter error', 'area error',
'smoothness error', 'compactness error', 'concavity error',
'concave points error', 'symmetry error', 'fractal dimension error',
'worst radius', 'worst texture', 'worst perimeter', 'worst area',
'worst smoothness', 'worst compactness', 'worst concavity',
'worst concave points', 'worst symmetry', 'worst fractal dimension',
'target'],
dtype='object')
In [34]:
sb.pairplot(data=df, hue= 'target' , vars=['mean radius','mean texture', 'mean perimeter','mean smoothness'])
plt.show()
In [36]:
df_corr = df[['mean radius','mean texture', 'mean perimeter','mean smoothness']].corr()
In [37]:
df_corr
Out[37]:
| mean radius | mean texture | mean perimeter | mean smoothness | |
|---|---|---|---|---|
| mean radius | 1.000000 | 0.323782 | 0.997855 | 0.170581 |
| mean texture | 0.323782 | 1.000000 | 0.329533 | -0.023389 |
| mean perimeter | 0.997855 | 0.329533 | 1.000000 | 0.207278 |
| mean smoothness | 0.170581 | -0.023389 | 0.207278 | 1.000000 |
In [ ]:
# 상관계수 결과는, 히트맵으로 같이 보여주자
In [49]:
sb.heatmap(data=df_corr, annot=True, fmt='.3f', cmap='coolwarm', linewidths=0.7, vmin= -1, vmax = 1)
plt.show()
In [51]:
df_all = df.corr()
In [58]:
plt.figure(figsize=(30,20))
sb.heatmap(data=df_all, annot=True, fmt='.1f', cmap='coolwarm', linewidths=1.0, vmin= -1, vmax = 1)
plt.show()
In [ ]:
In [ ]:
In [ ]:
STEP #4: MODEL TRAINING (FINDING A PROBLEM SOLUTION)¶
In [59]:
df.isna().sum()
Out[59]:
mean radius 0 mean texture 0 mean perimeter 0 mean area 0 mean smoothness 0 mean compactness 0 mean concavity 0 mean concave points 0 mean symmetry 0 mean fractal dimension 0 radius error 0 texture error 0 perimeter error 0 area error 0 smoothness error 0 compactness error 0 concavity error 0 concave points error 0 symmetry error 0 fractal dimension error 0 worst radius 0 worst texture 0 worst perimeter 0 worst area 0 worst smoothness 0 worst compactness 0 worst concavity 0 worst concave points 0 worst symmetry 0 worst fractal dimension 0 target 0 dtype: int64
In [60]:
df.head(3)
Out[60]:
| mean radius | mean texture | mean perimeter | mean area | mean smoothness | mean compactness | mean concavity | mean concave points | mean symmetry | mean fractal dimension | ... | worst texture | worst perimeter | worst area | worst smoothness | worst compactness | worst concavity | worst concave points | worst symmetry | worst fractal dimension | target | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 17.99 | 10.38 | 122.8 | 1001.0 | 0.11840 | 0.27760 | 0.3001 | 0.14710 | 0.2419 | 0.07871 | ... | 17.33 | 184.6 | 2019.0 | 0.1622 | 0.6656 | 0.7119 | 0.2654 | 0.4601 | 0.11890 | 0.0 |
| 1 | 20.57 | 17.77 | 132.9 | 1326.0 | 0.08474 | 0.07864 | 0.0869 | 0.07017 | 0.1812 | 0.05667 | ... | 23.41 | 158.8 | 1956.0 | 0.1238 | 0.1866 | 0.2416 | 0.1860 | 0.2750 | 0.08902 | 0.0 |
| 2 | 19.69 | 21.25 | 130.0 | 1203.0 | 0.10960 | 0.15990 | 0.1974 | 0.12790 | 0.2069 | 0.05999 | ... | 25.53 | 152.5 | 1709.0 | 0.1444 | 0.4245 | 0.4504 | 0.2430 | 0.3613 | 0.08758 | 0.0 |
3 rows × 31 columns
In [61]:
y = df["target"]
In [62]:
X = df.iloc[ : , :-2+1]
In [63]:
X.describe()
Out[63]:
| mean radius | mean texture | mean perimeter | mean area | mean smoothness | mean compactness | mean concavity | mean concave points | mean symmetry | mean fractal dimension | ... | worst radius | worst texture | worst perimeter | worst area | worst smoothness | worst compactness | worst concavity | worst concave points | worst symmetry | worst fractal dimension | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| count | 569.000000 | 569.000000 | 569.000000 | 569.000000 | 569.000000 | 569.000000 | 569.000000 | 569.000000 | 569.000000 | 569.000000 | ... | 569.000000 | 569.000000 | 569.000000 | 569.000000 | 569.000000 | 569.000000 | 569.000000 | 569.000000 | 569.000000 | 569.000000 |
| mean | 14.127292 | 19.289649 | 91.969033 | 654.889104 | 0.096360 | 0.104341 | 0.088799 | 0.048919 | 0.181162 | 0.062798 | ... | 16.269190 | 25.677223 | 107.261213 | 880.583128 | 0.132369 | 0.254265 | 0.272188 | 0.114606 | 0.290076 | 0.083946 |
| std | 3.524049 | 4.301036 | 24.298981 | 351.914129 | 0.014064 | 0.052813 | 0.079720 | 0.038803 | 0.027414 | 0.007060 | ... | 4.833242 | 6.146258 | 33.602542 | 569.356993 | 0.022832 | 0.157336 | 0.208624 | 0.065732 | 0.061867 | 0.018061 |
| min | 6.981000 | 9.710000 | 43.790000 | 143.500000 | 0.052630 | 0.019380 | 0.000000 | 0.000000 | 0.106000 | 0.049960 | ... | 7.930000 | 12.020000 | 50.410000 | 185.200000 | 0.071170 | 0.027290 | 0.000000 | 0.000000 | 0.156500 | 0.055040 |
| 25% | 11.700000 | 16.170000 | 75.170000 | 420.300000 | 0.086370 | 0.064920 | 0.029560 | 0.020310 | 0.161900 | 0.057700 | ... | 13.010000 | 21.080000 | 84.110000 | 515.300000 | 0.116600 | 0.147200 | 0.114500 | 0.064930 | 0.250400 | 0.071460 |
| 50% | 13.370000 | 18.840000 | 86.240000 | 551.100000 | 0.095870 | 0.092630 | 0.061540 | 0.033500 | 0.179200 | 0.061540 | ... | 14.970000 | 25.410000 | 97.660000 | 686.500000 | 0.131300 | 0.211900 | 0.226700 | 0.099930 | 0.282200 | 0.080040 |
| 75% | 15.780000 | 21.800000 | 104.100000 | 782.700000 | 0.105300 | 0.130400 | 0.130700 | 0.074000 | 0.195700 | 0.066120 | ... | 18.790000 | 29.720000 | 125.400000 | 1084.000000 | 0.146000 | 0.339100 | 0.382900 | 0.161400 | 0.317900 | 0.092080 |
| max | 28.110000 | 39.280000 | 188.500000 | 2501.000000 | 0.163400 | 0.345400 | 0.426800 | 0.201200 | 0.304000 | 0.097440 | ... | 36.040000 | 49.540000 | 251.200000 | 4254.000000 | 0.222600 | 1.058000 | 1.252000 | 0.291000 | 0.663800 | 0.207500 |
8 rows × 30 columns
In [64]:
from sklearn.preprocessing import StandardScaler
In [65]:
scaler_X = StandardScaler()
In [67]:
X = scaler_X.fit_transform(X)
In [70]:
from sklearn.model_selection import train_test_split
In [71]:
X_train, X_test, y_train, y_test = train_test_split(X,y, test_size=0.2, random_state=2)
In [72]:
from sklearn.svm import SVC
In [73]:
classifier = SVC(kernel="linear", random_state=2)
In [84]:
classifier2 = SVC(kernel="rbf", random_state=2)
In [77]:
classifier.fit(X_train,y_train)
In [85]:
classifier2.fit(X_train,y_train)
Out[85]:
SVC(random_state=2)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
SVC(random_state=2)
In [80]:
y_pred1= classifier.predict(X_test)
In [86]:
y_pred2= classifier2.predict(X_test)
In [81]:
from sklearn.metrics import confusion_matrix, accuracy_score
In [82]:
confusion_matrix(y_test, y_pred1)
Out[82]:
array([[44, 1],
[ 4, 65]], dtype=int64)
In [83]:
accuracy_score(y_test,y_pred1)
Out[83]:
0.956140350877193
In [87]:
confusion_matrix(y_test, y_pred2)
Out[87]:
array([[44, 1],
[ 3, 66]], dtype=int64)
In [88]:
accuracy_score(y_test,y_pred2)
Out[88]:
0.9649122807017544
In [ ]:
STEP #5: EVALUATING THE MODEL¶
In [89]:
# Grid Search
In [90]:
param_grid = { 'kernel' : ['linear','rbf','poly'], 'C' : [0.1, 1 , 10], "gamma" : [0.01, 0.1 , 1] }
In [91]:
from sklearn.model_selection import GridSearchCV
In [94]:
grid = GridSearchCV( SVC(), param_grid , refit = True, verbose= 4) # refit => 각 조합 마다 새로 학습해라.
# verbose => 사람한테 화면에 표시해라 (학습영향은 없으나 궁금하니까)
In [95]:
grid.fit(X_train,y_train)
Fitting 5 folds for each of 27 candidates, totalling 135 fits [CV 1/5] END ..C=0.1, gamma=0.01, kernel=linear;, score=0.978 total time= 0.0s [CV 2/5] END ..C=0.1, gamma=0.01, kernel=linear;, score=0.978 total time= 0.0s [CV 3/5] END ..C=0.1, gamma=0.01, kernel=linear;, score=0.978 total time= 0.0s [CV 4/5] END ..C=0.1, gamma=0.01, kernel=linear;, score=0.978 total time= 0.0s [CV 5/5] END ..C=0.1, gamma=0.01, kernel=linear;, score=0.967 total time= 0.0s [CV 1/5] END .....C=0.1, gamma=0.01, kernel=rbf;, score=0.912 total time= 0.0s [CV 2/5] END .....C=0.1, gamma=0.01, kernel=rbf;, score=0.934 total time= 0.0s [CV 3/5] END .....C=0.1, gamma=0.01, kernel=rbf;, score=0.967 total time= 0.0s [CV 4/5] END .....C=0.1, gamma=0.01, kernel=rbf;, score=0.956 total time= 0.0s [CV 5/5] END .....C=0.1, gamma=0.01, kernel=rbf;, score=0.934 total time= 0.0s [CV 1/5] END ....C=0.1, gamma=0.01, kernel=poly;, score=0.681 total time= 0.0s [CV 2/5] END ....C=0.1, gamma=0.01, kernel=poly;, score=0.659 total time= 0.0s [CV 3/5] END ....C=0.1, gamma=0.01, kernel=poly;, score=0.659 total time= 0.0s [CV 4/5] END ....C=0.1, gamma=0.01, kernel=poly;, score=0.670 total time= 0.0s [CV 5/5] END ....C=0.1, gamma=0.01, kernel=poly;, score=0.637 total time= 0.0s [CV 1/5] END ...C=0.1, gamma=0.1, kernel=linear;, score=0.978 total time= 0.0s [CV 2/5] END ...C=0.1, gamma=0.1, kernel=linear;, score=0.978 total time= 0.0s [CV 3/5] END ...C=0.1, gamma=0.1, kernel=linear;, score=0.978 total time= 0.0s [CV 4/5] END ...C=0.1, gamma=0.1, kernel=linear;, score=0.978 total time= 0.0s [CV 5/5] END ...C=0.1, gamma=0.1, kernel=linear;, score=0.967 total time= 0.0s [CV 1/5] END ......C=0.1, gamma=0.1, kernel=rbf;, score=0.901 total time= 0.0s [CV 2/5] END ......C=0.1, gamma=0.1, kernel=rbf;, score=0.967 total time= 0.0s [CV 3/5] END ......C=0.1, gamma=0.1, kernel=rbf;, score=0.956 total time= 0.0s [CV 4/5] END ......C=0.1, gamma=0.1, kernel=rbf;, score=0.956 total time= 0.0s [CV 5/5] END ......C=0.1, gamma=0.1, kernel=rbf;, score=0.923 total time= 0.0s [CV 1/5] END .....C=0.1, gamma=0.1, kernel=poly;, score=0.912 total time= 0.0s [CV 2/5] END .....C=0.1, gamma=0.1, kernel=poly;, score=0.934 total time= 0.0s [CV 3/5] END .....C=0.1, gamma=0.1, kernel=poly;, score=0.956 total time= 0.0s [CV 4/5] END .....C=0.1, gamma=0.1, kernel=poly;, score=0.945 total time= 0.0s [CV 5/5] END .....C=0.1, gamma=0.1, kernel=poly;, score=0.901 total time= 0.0s [CV 1/5] END .....C=0.1, gamma=1, kernel=linear;, score=0.978 total time= 0.0s [CV 2/5] END .....C=0.1, gamma=1, kernel=linear;, score=0.978 total time= 0.0s [CV 3/5] END .....C=0.1, gamma=1, kernel=linear;, score=0.978 total time= 0.0s [CV 4/5] END .....C=0.1, gamma=1, kernel=linear;, score=0.978 total time= 0.0s [CV 5/5] END .....C=0.1, gamma=1, kernel=linear;, score=0.967 total time= 0.0s [CV 1/5] END ........C=0.1, gamma=1, kernel=rbf;, score=0.637 total time= 0.0s [CV 2/5] END ........C=0.1, gamma=1, kernel=rbf;, score=0.637 total time= 0.0s [CV 3/5] END ........C=0.1, gamma=1, kernel=rbf;, score=0.637 total time= 0.0s [CV 4/5] END ........C=0.1, gamma=1, kernel=rbf;, score=0.626 total time= 0.0s [CV 5/5] END ........C=0.1, gamma=1, kernel=rbf;, score=0.626 total time= 0.0s [CV 1/5] END .......C=0.1, gamma=1, kernel=poly;, score=0.956 total time= 0.0s [CV 2/5] END .......C=0.1, gamma=1, kernel=poly;, score=0.923 total time= 0.0s [CV 3/5] END .......C=0.1, gamma=1, kernel=poly;, score=0.967 total time= 0.0s [CV 4/5] END .......C=0.1, gamma=1, kernel=poly;, score=0.989 total time= 0.0s [CV 5/5] END .......C=0.1, gamma=1, kernel=poly;, score=0.945 total time= 0.0s [CV 1/5] END ....C=1, gamma=0.01, kernel=linear;, score=0.956 total time= 0.0s [CV 2/5] END ....C=1, gamma=0.01, kernel=linear;, score=0.978 total time= 0.0s [CV 3/5] END ....C=1, gamma=0.01, kernel=linear;, score=0.978 total time= 0.0s [CV 4/5] END ....C=1, gamma=0.01, kernel=linear;, score=0.978 total time= 0.0s [CV 5/5] END ....C=1, gamma=0.01, kernel=linear;, score=0.967 total time= 0.0s [CV 1/5] END .......C=1, gamma=0.01, kernel=rbf;, score=0.956 total time= 0.0s [CV 2/5] END .......C=1, gamma=0.01, kernel=rbf;, score=0.978 total time= 0.0s [CV 3/5] END .......C=1, gamma=0.01, kernel=rbf;, score=0.989 total time= 0.0s [CV 4/5] END .......C=1, gamma=0.01, kernel=rbf;, score=0.967 total time= 0.0s [CV 5/5] END .......C=1, gamma=0.01, kernel=rbf;, score=0.956 total time= 0.0s [CV 1/5] END ......C=1, gamma=0.01, kernel=poly;, score=0.791 total time= 0.0s [CV 2/5] END ......C=1, gamma=0.01, kernel=poly;, score=0.714 total time= 0.0s [CV 3/5] END ......C=1, gamma=0.01, kernel=poly;, score=0.725 total time= 0.0s [CV 4/5] END ......C=1, gamma=0.01, kernel=poly;, score=0.769 total time= 0.0s [CV 5/5] END ......C=1, gamma=0.01, kernel=poly;, score=0.736 total time= 0.0s [CV 1/5] END .....C=1, gamma=0.1, kernel=linear;, score=0.956 total time= 0.0s [CV 2/5] END .....C=1, gamma=0.1, kernel=linear;, score=0.978 total time= 0.0s [CV 3/5] END .....C=1, gamma=0.1, kernel=linear;, score=0.978 total time= 0.0s [CV 4/5] END .....C=1, gamma=0.1, kernel=linear;, score=0.978 total time= 0.0s [CV 5/5] END .....C=1, gamma=0.1, kernel=linear;, score=0.967 total time= 0.0s [CV 1/5] END ........C=1, gamma=0.1, kernel=rbf;, score=0.934 total time= 0.0s [CV 2/5] END ........C=1, gamma=0.1, kernel=rbf;, score=0.978 total time= 0.0s [CV 3/5] END ........C=1, gamma=0.1, kernel=rbf;, score=0.967 total time= 0.0s [CV 4/5] END ........C=1, gamma=0.1, kernel=rbf;, score=0.956 total time= 0.0s [CV 5/5] END ........C=1, gamma=0.1, kernel=rbf;, score=0.945 total time= 0.0s [CV 1/5] END .......C=1, gamma=0.1, kernel=poly;, score=0.956 total time= 0.0s [CV 2/5] END .......C=1, gamma=0.1, kernel=poly;, score=0.967 total time= 0.0s [CV 3/5] END .......C=1, gamma=0.1, kernel=poly;, score=0.978 total time= 0.0s [CV 4/5] END .......C=1, gamma=0.1, kernel=poly;, score=0.956 total time= 0.0s [CV 5/5] END .......C=1, gamma=0.1, kernel=poly;, score=0.934 total time= 0.0s [CV 1/5] END .......C=1, gamma=1, kernel=linear;, score=0.956 total time= 0.0s [CV 2/5] END .......C=1, gamma=1, kernel=linear;, score=0.978 total time= 0.0s [CV 3/5] END .......C=1, gamma=1, kernel=linear;, score=0.978 total time= 0.0s [CV 4/5] END .......C=1, gamma=1, kernel=linear;, score=0.978 total time= 0.0s [CV 5/5] END .......C=1, gamma=1, kernel=linear;, score=0.967 total time= 0.0s [CV 1/5] END ..........C=1, gamma=1, kernel=rbf;, score=0.637 total time= 0.0s [CV 2/5] END ..........C=1, gamma=1, kernel=rbf;, score=0.648 total time= 0.0s [CV 3/5] END ..........C=1, gamma=1, kernel=rbf;, score=0.648 total time= 0.0s [CV 4/5] END ..........C=1, gamma=1, kernel=rbf;, score=0.626 total time= 0.0s [CV 5/5] END ..........C=1, gamma=1, kernel=rbf;, score=0.626 total time= 0.0s [CV 1/5] END .........C=1, gamma=1, kernel=poly;, score=0.956 total time= 0.0s [CV 2/5] END .........C=1, gamma=1, kernel=poly;, score=0.923 total time= 0.0s [CV 3/5] END .........C=1, gamma=1, kernel=poly;, score=0.967 total time= 0.0s [CV 4/5] END .........C=1, gamma=1, kernel=poly;, score=0.989 total time= 0.0s [CV 5/5] END .........C=1, gamma=1, kernel=poly;, score=0.945 total time= 0.0s [CV 1/5] END ...C=10, gamma=0.01, kernel=linear;, score=0.945 total time= 0.0s [CV 2/5] END ...C=10, gamma=0.01, kernel=linear;, score=0.945 total time= 0.0s [CV 3/5] END ...C=10, gamma=0.01, kernel=linear;, score=0.967 total time= 0.0s [CV 4/5] END ...C=10, gamma=0.01, kernel=linear;, score=0.956 total time= 0.0s [CV 5/5] END ...C=10, gamma=0.01, kernel=linear;, score=0.967 total time= 0.0s [CV 1/5] END ......C=10, gamma=0.01, kernel=rbf;, score=0.967 total time= 0.0s [CV 2/5] END ......C=10, gamma=0.01, kernel=rbf;, score=0.989 total time= 0.0s [CV 3/5] END ......C=10, gamma=0.01, kernel=rbf;, score=1.000 total time= 0.0s [CV 4/5] END ......C=10, gamma=0.01, kernel=rbf;, score=0.978 total time= 0.0s [CV 5/5] END ......C=10, gamma=0.01, kernel=rbf;, score=0.978 total time= 0.0s [CV 1/5] END .....C=10, gamma=0.01, kernel=poly;, score=0.857 total time= 0.0s [CV 2/5] END .....C=10, gamma=0.01, kernel=poly;, score=0.791 total time= 0.0s [CV 3/5] END .....C=10, gamma=0.01, kernel=poly;, score=0.879 total time= 0.0s [CV 4/5] END .....C=10, gamma=0.01, kernel=poly;, score=0.879 total time= 0.0s [CV 5/5] END .....C=10, gamma=0.01, kernel=poly;, score=0.868 total time= 0.0s [CV 1/5] END ....C=10, gamma=0.1, kernel=linear;, score=0.945 total time= 0.0s [CV 2/5] END ....C=10, gamma=0.1, kernel=linear;, score=0.945 total time= 0.0s [CV 3/5] END ....C=10, gamma=0.1, kernel=linear;, score=0.967 total time= 0.0s [CV 4/5] END ....C=10, gamma=0.1, kernel=linear;, score=0.956 total time= 0.0s [CV 5/5] END ....C=10, gamma=0.1, kernel=linear;, score=0.967 total time= 0.0s [CV 1/5] END .......C=10, gamma=0.1, kernel=rbf;, score=0.912 total time= 0.0s [CV 2/5] END .......C=10, gamma=0.1, kernel=rbf;, score=0.956 total time= 0.0s [CV 3/5] END .......C=10, gamma=0.1, kernel=rbf;, score=0.956 total time= 0.0s [CV 4/5] END .......C=10, gamma=0.1, kernel=rbf;, score=0.967 total time= 0.0s [CV 5/5] END .......C=10, gamma=0.1, kernel=rbf;, score=0.967 total time= 0.0s [CV 1/5] END ......C=10, gamma=0.1, kernel=poly;, score=0.956 total time= 0.0s [CV 2/5] END ......C=10, gamma=0.1, kernel=poly;, score=0.934 total time= 0.0s [CV 3/5] END ......C=10, gamma=0.1, kernel=poly;, score=0.978 total time= 0.0s [CV 4/5] END ......C=10, gamma=0.1, kernel=poly;, score=0.978 total time= 0.0s [CV 5/5] END ......C=10, gamma=0.1, kernel=poly;, score=0.945 total time= 0.0s [CV 1/5] END ......C=10, gamma=1, kernel=linear;, score=0.945 total time= 0.0s [CV 2/5] END ......C=10, gamma=1, kernel=linear;, score=0.945 total time= 0.0s [CV 3/5] END ......C=10, gamma=1, kernel=linear;, score=0.967 total time= 0.0s [CV 4/5] END ......C=10, gamma=1, kernel=linear;, score=0.956 total time= 0.0s [CV 5/5] END ......C=10, gamma=1, kernel=linear;, score=0.967 total time= 0.0s [CV 1/5] END .........C=10, gamma=1, kernel=rbf;, score=0.637 total time= 0.0s [CV 2/5] END .........C=10, gamma=1, kernel=rbf;, score=0.648 total time= 0.0s [CV 3/5] END .........C=10, gamma=1, kernel=rbf;, score=0.648 total time= 0.0s [CV 4/5] END .........C=10, gamma=1, kernel=rbf;, score=0.626 total time= 0.0s [CV 5/5] END .........C=10, gamma=1, kernel=rbf;, score=0.626 total time= 0.0s [CV 1/5] END ........C=10, gamma=1, kernel=poly;, score=0.956 total time= 0.0s [CV 2/5] END ........C=10, gamma=1, kernel=poly;, score=0.923 total time= 0.0s [CV 3/5] END ........C=10, gamma=1, kernel=poly;, score=0.967 total time= 0.0s [CV 4/5] END ........C=10, gamma=1, kernel=poly;, score=0.989 total time= 0.0s [CV 5/5] END ........C=10, gamma=1, kernel=poly;, score=0.945 total time= 0.0s
Out[95]:
GridSearchCV(estimator=SVC(),
param_grid={'C': [0.1, 1, 10], 'gamma': [0.01, 0.1, 1],
'kernel': ['linear', 'rbf', 'poly']},
verbose=4)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
GridSearchCV(estimator=SVC(),
param_grid={'C': [0.1, 1, 10], 'gamma': [0.01, 0.1, 1],
'kernel': ['linear', 'rbf', 'poly']},
verbose=4)SVC()
SVC()
In [97]:
classifier = grid.best_estimator_ # 커널은 rbf
In [99]:
classifier
Out[99]:
SVC(C=10, gamma=0.01)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
SVC(C=10, gamma=0.01)
In [98]:
grid.best_params_
Out[98]:
{'C': 10, 'gamma': 0.01, 'kernel': 'rbf'}
In [100]:
grid.best_score_
Out[100]:
0.9824175824175825
In [102]:
y_pred = classifier.predict(X_test)
In [103]:
confusion_matrix(y_test, y_pred)
Out[103]:
array([[44, 1],
[ 2, 67]], dtype=int64)
In [104]:
accuracy_score(y_test,y_pred)
Out[104]:
0.9736842105263158
