In [ ]:
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.neural_network import MLPClassifier
from sklearn.metrics import classification_report
import seaborn as sns
import matplotlib.pyplot as plt
In [ ]:
df = pd.read_csv('cancer.csv')
df.head()
Out[ ]:
diagnosis radius_mean texture_mean perimeter_mean area_mean smoothness_mean compactness_mean
0 M 17.99 10.38 122.80 1001.0 0.11840 0.27760
1 M 20.57 17.77 132.90 1326.0 0.08474 0.07864
2 M 19.69 21.25 130.00 1203.0 0.10960 0.15990
3 M 11.42 20.38 77.58 386.1 0.14250 0.28390
4 M 20.29 14.34 135.10 1297.0 0.10030 0.13280
In [ ]:
# look at diagnisis category with data exploration
len(df)
Out[ ]:
570
In [ ]:
df['diagnosis'].value_counts()
Out[ ]:
count
diagnosis
B 357
M 213

In [ ]:
df.isnull().sum()
Out[ ]:
0
diagnosis 0
radius_mean 0
texture_mean 0
perimeter_mean 0
area_mean 0
smoothness_mean 0
compactness_mean 0

In [ ]:
#radius_mean
sns.kdeplot(data=df, x='radius_mean', hue= 'diagnosis', common_norm= False,
            fill=True)
plt.show()
No description has been provided for this image
In [ ]:
features = df.iloc[:,1:7]
features.head()
Out[ ]:
radius_mean texture_mean perimeter_mean area_mean smoothness_mean compactness_mean
0 17.99 10.38 122.80 1001.0 0.11840 0.27760
1 20.57 17.77 132.90 1326.0 0.08474 0.07864
2 19.69 21.25 130.00 1203.0 0.10960 0.15990
3 11.42 20.38 77.58 386.1 0.14250 0.28390
4 20.29 14.34 135.10 1297.0 0.10030 0.13280
In [ ]:
label = df.iloc[:,0]
label.head()
Out[ ]:
diagnosis
0 M
1 M
2 M
3 M
4 M

In [ ]:
#data normalization (standard)
std_scaler = StandardScaler()
#normalize data
features_scaled = std_scaler.fit_transform(features)
features_scaled = pd.DataFrame(features_scaled, columns= features.columns, index= features.index)
features_scaled.head()
Out[ ]:
radius_mean texture_mean perimeter_mean area_mean smoothness_mean compactness_mean
0 1.096320 -2.072462 1.269364 0.983936 1.570347 3.286462
1 1.829403 -0.356089 1.685585 1.908811 -0.825701 -0.487431
2 1.579360 0.452162 1.566076 1.558781 0.943929 1.053917
3 -0.770485 0.250099 -0.594153 -0.765926 3.285878 3.405961
4 1.749844 -1.152728 1.776248 1.826283 0.281919 0.539881
In [ ]:
train_x, test_x, train_y, test_y = train_test_split(features_scaled, label,
                                                    test_size=0.2,
                                                    random_state=1)
In [ ]:
#classifier
clf = MLPClassifier(hidden_layer_sizes=(4, 3), solver= 'lbfgs',
                    alpha=1e-5, random_state=1)
#create model
clf.fit(train_x, train_y)
Out[ ]:
MLPClassifier(alpha=1e-05, hidden_layer_sizes=(4, 3), random_state=1,
              solver='lbfgs')
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.
MLPClassifier(alpha=1e-05, hidden_layer_sizes=(4, 3), random_state=1,
              solver='lbfgs')
In [ ]:
#predict
pred_y = clf.predict(test_x)
In [ ]:
rp = classification_report(test_y, pred_y)
print(rp)

              precision    recall  f1-score   support

           B       0.84      0.95      0.89        65
           M       0.93      0.76      0.83        49

    accuracy                           0.87       114
   macro avg       0.88      0.85      0.86       114
weighted avg       0.88      0.87      0.87       114