Permalink
Name already in use
A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
CSE5713_DataMiningProject/bcw.py
Go to fileThis commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
130 lines (115 sloc)
4.25 KB
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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() |