bcw.py

import pandas as pd
import seaborn as sn
import matplotlib.pyplot as plt
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.manifold import TSNE
from mpl_toolkits.mplot3d import Axes3D
import seaborn as sns
from sklearn.neural_network import MLPClassifier
from sklearn.model_selection import train_test_split

df=pd.read_csv('breast-cancer-wisconsin.csv')
features = ['clumpthickness', 'cellsize', 'cellshape', 'marginaladhesion','singleepithelialcellsize','barenuclei','blandchromatin','normalnucleoli','mitoses']

#impute missing values (all of which are in barenuclei) with mean of barenuclei
df=df.replace('?',3.54465593)

# miss=[617,411,321,315,297,294,292,275,249,235,164,158,145,139,40,23]
# for ind in miss:
#     df=df.drop(df.index[ind])

# Separating out the features
x = df.loc[:, features].values# Separating out the target
y = df.loc[:,['samplecodenumber','class']].values# Standardizing the features
x = StandardScaler().fit_transform(x)
#print(y)

def classify(hlsize):
    X_train, X_test, y_trainid, y_testid = train_test_split(x, y, test_size=0.3, random_state=1)
    y_test=y_testid[:,1]
    y_train=y_trainid[:,1]
    #print(y_test)

    clf = MLPClassifier(solver='lbfgs', alpha=1e-5, hidden_layer_sizes=hlsize, random_state=1)

    clf.fit(X_train, y_train)
    y_pred=clf.predict(X_test)
    file.write("samplecodenumber,trueclass,predclass \n")
    for i in range(len(y_pred)):
        file.write(str(y_testid[i,0])+","+str(y_testid[i,1])+','+str(y_pred[i])+'\n')
    tpr=0#positive=benign=2
    fpr=0
    tnr=0
    fnr=0
    for i in range(len(y_test)):
        if y_test[i]==y_pred[i]:
            if y_test[i]==2:
                tpr+=1
            else:
                tnr+=1
        elif y_test[i]==2:
            fnr+=1
        else:
            fpr+=1


    temp=tpr+fnr
    if temp>0:
        temp=fpr+tnr
        if temp>0:
            temp=tpr+fpr
            if temp>0:
                temp=tpr+fnr
                if temp>0:
                    tprate= tpr/(tpr+fnr)
                    fprate= fpr/(fpr+tnr)

                    #print(tprate,fprate)
                    precision= tpr/(tpr+fpr)
                    recall= tpr/(tpr+fnr)

                    #print("recall=",recall)
                    acc=(tpr+tnr)/(tpr+fpr+tnr+fnr)

                    if acc>.965:
                        file.write("hlsize ="+str(hlsize)+'\n')
                        file.write("true pos rate="+str(tprate)+'\n')
                        file.write("false pos rate="+str(fprate)+'\n')
                        file.write("precision="+str(precision)+'\n')
                        file.write("accuracy="+str(acc)+'\n')

file = open('res.txt','w')
classify((13,8,18))
#
# for a in range(20):
#      if a>0:
#          for b in range(20):
#              if b>0:
#                  for c in range(20):
#                      if c>0:
#                         classify((a,b,c))

# tsne = TSNE(n_components=2, verbose=1, perplexity=60, n_iter=500)
# tsne_results = tsne.fit_transform(df_x)
# #print('t-SNE done! Time elapsed: {} seconds'.format(time.time()-time_start))
#
# df_x['tsne-2d-one'] = tsne_results[:,0]
# df_x['tsne-2d-two'] = tsne_results[:,1]
# df_x['target'] = targ['class']
# plt.figure(figsize=(16,10))
# sns.scatterplot(
#     x="tsne-2d-one", y="tsne-2d-two",
#     hue="target",
#     palette=sns.color_palette("hls", 2),
#     data=df_x,
#     legend="full",
#     alpha=0.3
# )

# pca = PCA(n_components=3)
# principalComponents = pca.fit_transform(x)
# principalDf = pd.DataFrame(data = principalComponents, columns = ['principal component 1', 'principal component 2','principal component 3'])
# finalDf = pd.concat([principalDf, df[['class']]], axis = 1)
#
# fig = plt.figure(figsize = (8,8))
# ax = fig.add_subplot(1,1,1)
# ax.set_xlabel('Principal Component 1', fontsize = 15)
# ax.set_ylabel('Principal Component 2', fontsize = 15)
# ax.set_title('2 component PCA', fontsize = 20)
# targets = [2,4]
# colors = ['r', 'g']
# for target, color in zip(targets,colors):
#     indicesToKeep = finalDf['class'] == target
#     ax.scatter(finalDf.loc[indicesToKeep, 'principal component 1']
#                , finalDf.loc[indicesToKeep, 'principal component 2']
#                , c = color
#                , s = 10)
# ax.legend(targets)
# ax.grid()
plt.show()