add files

banknote_detection.py

+#!/usr/bin/python3
+
+from keras.models import Sequential
+from keras.layers import Dense
+from numpy import loadtxt
+
+data = loadtxt('data_banknote_authentication.txt', delimiter=',')
+
+inputs = data[:,0:4]
+outputs = data[:,4]
+
+model = Sequential()
+
+model.add(Dense(6, input_dim=4, activation='relu'))
+model.add(Dense(3, activation='relu'))
+model.add(Dense(1, activation='sigmoid'))
+
+model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
+model.fit(inputs, outputs, epochs=100, batch_size=10)
+
+_, accuracy = model.evaluate(inputs, outputs)
+print(accuracy)

haberman.data

+30,64,1,1
+30,62,3,1
+30,65,0,1
+31,59,2,1
+31,65,4,1
+33,58,10,1
+33,60,0,1
+34,59,0,2
+34,66,9,2
+34,58,30,1
+34,60,1,1
+34,61,10,1
+34,67,7,1
+34,60,0,1
+35,64,13,1
+35,63,0,1
+36,60,1,1
+36,69,0,1
+37,60,0,1
+37,63,0,1
+37,58,0,1
+37,59,6,1
+37,60,15,1
+37,63,0,1
+38,69,21,2
+38,59,2,1
+38,60,0,1
+38,60,0,1
+38,62,3,1
+38,64,1,1
+38,66,0,1
+38,66,11,1
+38,60,1,1
+38,67,5,1
+39,66,0,2
+39,63,0,1
+39,67,0,1
+39,58,0,1
+39,59,2,1
+39,63,4,1
+40,58,2,1
+40,58,0,1
+40,65,0,1
+41,60,23,2
+41,64,0,2
+41,67,0,2
+41,58,0,1
+41,59,8,1
+41,59,0,1
+41,64,0,1
+41,69,8,1
+41,65,0,1
+41,65,0,1
+42,69,1,2
+42,59,0,2
+42,58,0,1
+42,60,1,1
+42,59,2,1
+42,61,4,1
+42,62,20,1
+42,65,0,1
+42,63,1,1
+43,58,52,2
+43,59,2,2
+43,64,0,2
+43,64,0,2
+43,63,14,1
+43,64,2,1
+43,64,3,1
+43,60,0,1
+43,63,2,1
+43,65,0,1
+43,66,4,1
+44,64,6,2
+44,58,9,2
+44,63,19,2
+44,61,0,1
+44,63,1,1
+44,61,0,1
+44,67,16,1
+45,65,6,2
+45,66,0,2
+45,67,1,2
+45,60,0,1
+45,67,0,1
+45,59,14,1
+45,64,0,1
+45,68,0,1
+45,67,1,1
+46,58,2,2
+46,69,3,2
+46,62,5,2
+46,65,20,2
+46,62,0,1
+46,58,3,1
+46,63,0,1
+47,63,23,2
+47,62,0,2
+47,65,0,2
+47,61,0,1
+47,63,6,1
+47,66,0,1
+47,67,0,1
+47,58,3,1
+47,60,4,1
+47,68,4,1
+47,66,12,1
+48,58,11,2
+48,58,11,2
+48,67,7,2
+48,61,8,1
+48,62,2,1
+48,64,0,1
+48,66,0,1
+49,63,0,2
+49,64,10,2
+49,61,1,1
+49,62,0,1
+49,66,0,1
+49,60,1,1
+49,62,1,1
+49,63,3,1
+49,61,0,1
+49,67,1,1
+50,63,13,2
+50,64,0,2
+50,59,0,1
+50,61,6,1
+50,61,0,1
+50,63,1,1
+50,58,1,1
+50,59,2,1
+50,61,0,1
+50,64,0,1
+50,65,4,1
+50,66,1,1
+51,59,13,2
+51,59,3,2
+51,64,7,1
+51,59,1,1
+51,65,0,1
+51,66,1,1
+52,69,3,2
+52,59,2,2
+52,62,3,2
+52,66,4,2
+52,61,0,1
+52,63,4,1
+52,69,0,1
+52,60,4,1
+52,60,5,1
+52,62,0,1
+52,62,1,1
+52,64,0,1
+52,65,0,1
+52,68,0,1
+53,58,4,2
+53,65,1,2
+53,59,3,2
+53,60,9,2
+53,63,24,2
+53,65,12,2
+53,58,1,1
+53,60,1,1
+53,60,2,1
+53,61,1,1
+53,63,0,1
+54,60,11,2
+54,65,23,2
+54,65,5,2
+54,68,7,2
+54,59,7,1
+54,60,3,1
+54,66,0,1
+54,67,46,1
+54,62,0,1
+54,69,7,1
+54,63,19,1
+54,58,1,1
+54,62,0,1
+55,63,6,2
+55,68,15,2
+55,58,1,1
+55,58,0,1
+55,58,1,1
+55,66,18,1
+55,66,0,1
+55,69,3,1
+55,69,22,1
+55,67,1,1
+56,65,9,2
+56,66,3,2
+56,60,0,1
+56,66,2,1
+56,66,1,1
+56,67,0,1
+56,60,0,1
+57,61,5,2
+57,62,14,2
+57,64,1,2
+57,64,9,1
+57,69,0,1
+57,61,0,1
+57,62,0,1
+57,63,0,1
+57,64,0,1
+57,64,0,1
+57,67,0,1
+58,59,0,1
+58,60,3,1
+58,61,1,1
+58,67,0,1
+58,58,0,1
+58,58,3,1
+58,61,2,1
+59,62,35,2
+59,60,0,1
+59,63,0,1
+59,64,1,1
+59,64,4,1
+59,64,0,1
+59,64,7,1
+59,67,3,1
+60,59,17,2
+60,65,0,2
+60,61,1,1
+60,67,2,1
+60,61,25,1
+60,64,0,1
+61,62,5,2
+61,65,0,2
+61,68,1,2
+61,59,0,1
+61,59,0,1
+61,64,0,1
+61,65,8,1
+61,68,0,1
+61,59,0,1
+62,59,13,2
+62,58,0,2
+62,65,19,2
+62,62,6,1
+62,66,0,1
+62,66,0,1
+62,58,0,1
+63,60,1,2
+63,61,0,1
+63,62,0,1
+63,63,0,1
+63,63,0,1
+63,66,0,1
+63,61,9,1
+63,61,28,1
+64,58,0,1
+64,65,22,1
+64,66,0,1
+64,61,0,1
+64,68,0,1
+65,58,0,2
+65,61,2,2
+65,62,22,2
+65,66,15,2
+65,58,0,1
+65,64,0,1
+65,67,0,1
+65,59,2,1
+65,64,0,1
+65,67,1,1
+66,58,0,2
+66,61,13,2
+66,58,0,1
+66,58,1,1
+66,68,0,1
+67,64,8,2
+67,63,1,2
+67,66,0,1
+67,66,0,1
+67,61,0,1
+67,65,0,1
+68,67,0,1
+68,68,0,1
+69,67,8,2
+69,60,0,1
+69,65,0,1
+69,66,0,1
+70,58,0,2
+70,58,4,2
+70,66,14,1
+70,67,0,1
+70,68,0,1
+70,59,8,1
+70,63,0,1
+71,68,2,1
+72,63,0,2
+72,58,0,1
+72,64,0,1
+72,67,3,1
+73,62,0,1
+73,68,0,1
+74,65,3,2
+74,63,0,1
+75,62,1,1
+76,67,0,1
+77,65,3,1
+78,65,1,2
+83,58,2,2

haberman.names

+1. Title: Haberman's Survival Data
+
+2. Sources:
+   (a) Donor:   Tjen-Sien Lim (limt@stat.wisc.edu)
+   (b) Date:    March 4, 1999
+
+3. Past Usage:
+   1. Haberman, S. J. (1976). Generalized Residuals for Log-Linear
+      Models, Proceedings of the 9th International Biometrics
+      Conference, Boston, pp. 104-122.
+   2. Landwehr, J. M., Pregibon, D., and Shoemaker, A. C. (1984),
+      Graphical Models for Assessing Logistic Regression Models (with
+      discussion), Journal of the American Statistical Association 79:
+      61-83.
+   3. Lo, W.-D. (1993). Logistic Regression Trees, PhD thesis,
+      Department of Statistics, University of Wisconsin, Madison, WI.
+
+4. Relevant Information:
+   The dataset contains cases from a study that was conducted between
+   1958 and 1970 at the University of Chicago's Billings Hospital on
+   the survival of patients who had undergone surgery for breast
+   cancer.
+
+5. Number of Instances: 306
+
+6. Number of Attributes: 4 (including the class attribute)
+
+7. Attribute Information:
+   1. Age of patient at time of operation (numerical)
+   2. Patient's year of operation (year - 1900, numerical)
+   3. Number of positive axillary nodes detected (numerical)
+   4. Survival status (class attribute)
+         1 = the patient survived 5 years or longer
+         2 = the patient died within 5 year
+
+8. Missing Attribute Values: None

survival.py

+#!/usr/bin/python3
+
+from keras.models import Sequential
+from keras.layers import Dense
+from numpy import loadtxt
+import numpy as np
+
+data = loadtxt('haberman.data', delimiter=',')
+
+for i in range(306):
+    if(data[i,3]==1.0):
+        data[i,3]=0
+    else:
+        data[i,3]=1
+
+
+
+inputs = data[:,0:3]
+outputs = data[:,3]
+
+model = Sequential()
+
+model.add(Dense(6, input_dim=3, activation='relu'))
+model.add(Dense(8, activation='relu'))
+model.add(Dense(1, activation='sigmoid'))
+
+model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
+model.fit(inputs, outputs, epochs=30, batch_size=10)
+
+_, accuracy = model.evaluate(inputs, outputs)
+print(accuracy)
+#print(inputs[6:8])
+#print(model.predict(np.array(inputs[6:8])))
+#print(model.get_weights())
+#weights = model.get_weights()
+#model.set_weights(weights)
+#print(model.get_weights())