import numpy as np

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
warnings.filterwarnings('ignore')
import tensorflow as tf
from tensorflow.keras import Sequential
from tensorflow.keras.layers import Dense
from sklearn.metrics import accuracy_score, confusion_matrix
from sklearn.metrics import mean_squared_error

df = pd.read_excel("cancer_classification.xlsx")

df.corr()

mean radius mean texture mean perimeter

mean area \
mean radius 1.000000 0.323782 0.997855
0.987357
mean texture 0.323782 1.000000 0.329533
0.321086
mean perimeter 0.997855 0.329533 1.000000
0.986507
mean area 0.987357 0.321086 0.986507
1.000000
mean smoothness 0.170581 -0.023389 0.207278
0.177028
mean compactness 0.506124 0.236702 0.556936
0.498502
mean concavity 0.676764 0.302418 0.716136
0.685983
mean concave points 0.822529 0.293464 0.850977
0.823269
mean symmetry 0.147741 0.071401 0.183027
0.151293
mean fractal dimension -0.311631 -0.076437 -0.261477 -
0.283110
radius error 0.679090 0.275869 0.691765
0.732562
texture error -0.097317 0.386358 -0.086761 -
0.066280
perimeter error 0.674172 0.281673 0.693135
0.726628
area error 0.735864 0.259845 0.744983
0.800086
smoothness error -0.222600 0.006614 -0.202694 -
0.166777
compactness error 0.206000 0.191975 0.250744
0.212583
concavity error 0.194204 0.143293 0.228082
0.207660
concave points error 0.376169 0.163851 0.407217
0.372320
symmetry error -0.104321 0.009127 -0.081629 -
0.072497
fractal dimension error -0.042641 0.054458 -0.005523 -
0.019887
worst radius 0.969539 0.352573 0.969476
0.962746
worst texture 0.297008 0.912045 0.303038
0.287489
worst perimeter 0.965137 0.358040 0.970387
0.959120
worst area 0.941082 0.343546 0.941550
0.959213
worst smoothness 0.119616 0.077503 0.150549
0.123523
worst compactness 0.413463 0.277830 0.455774
0.390410
worst concavity 0.526911 0.301025 0.563879
0.512606
worst concave points 0.744214 0.295316 0.771241
0.722017
worst symmetry 0.163953 0.105008 0.189115
0.143570
worst fractal dimension 0.007066 0.119205 0.051019
0.003738
target -0.730029 -0.415185 -0.742636 -
0.708984

mean smoothness mean compactness mean

concavity \
mean radius 0.170581 0.506124
0.676764
mean texture -0.023389 0.236702
0.302418
mean perimeter 0.207278 0.556936
0.716136
mean area 0.177028 0.498502
0.685983
mean smoothness 1.000000 0.659123
0.521984
mean compactness 0.659123 1.000000
0.883121
mean concavity 0.521984 0.883121
1.000000
mean concave points 0.553695 0.831135
0.921391
mean symmetry 0.557775 0.602641
0.500667
mean fractal dimension 0.584792 0.565369
0.336783
radius error 0.301467 0.497473
0.631925
texture error 0.068406 0.046205
0.076218
perimeter error 0.296092 0.548905
0.660391
area error 0.246552 0.455653
0.617427
smoothness error 0.332375 0.135299
0.098564
compactness error 0.318943 0.738722
0.670279
concavity error 0.248396 0.570517
0.691270
concave points error 0.380676 0.642262
0.683260
symmetry error 0.200774 0.229977
0.178009
fractal dimension error 0.283607 0.507318
0.449301
worst radius 0.213120 0.535315
0.688236
worst texture 0.036072 0.248133
0.299879
worst perimeter 0.238853 0.590210
0.729565
worst area 0.206718 0.509604
0.675987
worst smoothness 0.805324 0.565541
0.448822
worst compactness 0.472468 0.865809
0.754968
worst concavity 0.434926 0.816275
0.884103
worst concave points 0.503053 0.815573
0.861323
worst symmetry 0.394309 0.510223
0.409464
worst fractal dimension 0.499316 0.687382
0.514930
target -0.358560 -0.596534 -
0.696360

mean concave points mean symmetry \

mean radius 0.822529 0.147741
mean texture 0.293464 0.071401
mean perimeter 0.850977 0.183027
mean area 0.823269 0.151293
mean smoothness 0.553695 0.557775
mean compactness 0.831135 0.602641
mean concavity 0.921391 0.500667
mean concave points 1.000000 0.462497
mean symmetry 0.462497 1.000000
mean fractal dimension 0.166917 0.479921
radius error 0.698050 0.303379
texture error 0.021480 0.128053
perimeter error 0.710650 0.313893
area error 0.690299 0.223970
smoothness error 0.027653 0.187321
compactness error 0.490424 0.421659
concavity error 0.439167 0.342627
concave points error 0.615634 0.393298
symmetry error 0.095351 0.449137
fractal dimension error 0.257584 0.331786
worst radius 0.830318 0.185728
worst texture 0.292752 0.090651
worst perimeter 0.855923 0.219169
worst area 0.809630 0.177193
worst smoothness 0.452753 0.426675
worst compactness 0.667454 0.473200
worst concavity 0.752399 0.433721
worst concave points 0.910155 0.430297
worst symmetry 0.375744 0.699826
worst fractal dimension 0.368661 0.438413
target -0.776614 -0.330499

mean fractal dimension ... worst texture \

mean radius -0.311631 ... 0.297008
mean texture -0.076437 ... 0.912045
mean perimeter -0.261477 ... 0.303038
mean area -0.283110 ... 0.287489
mean smoothness 0.584792 ... 0.036072
mean compactness 0.565369 ... 0.248133
mean concavity 0.336783 ... 0.299879
mean concave points 0.166917 ... 0.292752
mean symmetry 0.479921 ... 0.090651
mean fractal dimension 1.000000 ... -0.051269
radius error 0.000111 ... 0.194799
texture error 0.164174 ... 0.409003
perimeter error 0.039830 ... 0.200371
area error -0.090170 ... 0.196497
smoothness error 0.401964 ... -0.074743
compactness error 0.559837 ... 0.143003
concavity error 0.446630 ... 0.100241
concave points error 0.341198 ... 0.086741
symmetry error 0.345007 ... -0.077473
fractal dimension error 0.688132 ... -0.003195
worst radius -0.253691 ... 0.359921
worst texture -0.051269 ... 1.000000
worst perimeter -0.205151 ... 0.365098
worst area -0.231854 ... 0.345842
worst smoothness 0.504942 ... 0.225429
worst compactness 0.458798 ... 0.360832
worst concavity 0.346234 ... 0.368366
worst concave points 0.175325 ... 0.359755
worst symmetry 0.334019 ... 0.233027
worst fractal dimension 0.767297 ... 0.219122
target 0.012838 ... -0.456903

worst perimeter worst area worst smoothness

\
mean radius 0.965137 0.941082 0.119616

mean texture 0.358040 0.343546 0.077503

mean perimeter 0.970387 0.941550 0.150549

mean area 0.959120 0.959213 0.123523

mean smoothness 0.238853 0.206718 0.805324

mean compactness 0.590210 0.509604 0.565541

mean concavity 0.729565 0.675987 0.448822

mean concave points 0.855923 0.809630 0.452753

mean symmetry 0.219169 0.177193 0.426675

mean fractal dimension -0.205151 -0.231854 0.504942

radius error 0.719684 0.751548 0.141919

texture error -0.102242 -0.083195 -0.073658

perimeter error 0.721031 0.730713 0.130054

area error 0.761213 0.811408 0.125389

smoothness error -0.217304 -0.182195 0.314457

compactness error 0.260516 0.199371 0.227394

concavity error 0.226680 0.188353 0.168481

concave points error 0.394999 0.342271 0.215351

symmetry error -0.103753 -0.110343 -0.012662

fractal dimension error -0.001000 -0.022736 0.170568

worst radius 0.993708 0.984015 0.216574

worst texture 0.365098 0.345842 0.225429

worst perimeter 1.000000 0.977578 0.236775

worst area 0.977578 1.000000 0.209145

worst smoothness 0.236775 0.209145 1.000000

worst compactness 0.529408 0.438296 0.568187

worst concavity 0.618344 0.543331 0.518523

worst concave points 0.816322 0.747419 0.547691

worst symmetry 0.269493 0.209146 0.493838

worst fractal dimension 0.138957 0.079647 0.617624

target -0.782914 -0.733825 -0.421465

worst compactness worst concavity \

mean radius 0.413463 0.526911
mean texture 0.277830 0.301025
mean perimeter 0.455774 0.563879
mean area 0.390410 0.512606
mean smoothness 0.472468 0.434926
mean compactness 0.865809 0.816275
mean concavity 0.754968 0.884103
mean concave points 0.667454 0.752399
mean symmetry 0.473200 0.433721
mean fractal dimension 0.458798 0.346234
radius error 0.287103 0.380585
texture error -0.092439 -0.068956
perimeter error 0.341919 0.418899
area error 0.283257 0.385100
smoothness error -0.055558 -0.058298
compactness error 0.678780 0.639147
concavity error 0.484858 0.662564
concave points error 0.452888 0.549592
symmetry error 0.060255 0.037119
fractal dimension error 0.390159 0.379975
worst radius 0.475820 0.573975
worst texture 0.360832 0.368366
worst perimeter 0.529408 0.618344
worst area 0.438296 0.543331
worst smoothness 0.568187 0.518523
worst compactness 1.000000 0.892261
worst concavity 0.892261 1.000000
worst concave points 0.801080 0.855434
worst symmetry 0.614441 0.532520
worst fractal dimension 0.810455 0.686511
target -0.590998 -0.659610

worst concave points worst symmetry \

mean radius 0.744214 0.163953
mean texture 0.295316 0.105008
mean perimeter 0.771241 0.189115
mean area 0.722017 0.143570
mean smoothness 0.503053 0.394309
mean compactness 0.815573 0.510223
mean concavity 0.861323 0.409464
mean concave points 0.910155 0.375744
mean symmetry 0.430297 0.699826
mean fractal dimension 0.175325 0.334019
radius error 0.531062 0.094543
texture error -0.119638 -0.128215
perimeter error 0.554897 0.109930
area error 0.538166 0.074126
smoothness error -0.102007 -0.107342
compactness error 0.483208 0.277878
concavity error 0.440472 0.197788
concave points error 0.602450 0.143116
symmetry error -0.030413 0.389402
fractal dimension error 0.215204 0.111094
worst radius 0.787424 0.243529
worst texture 0.359755 0.233027
worst perimeter 0.816322 0.269493
worst area 0.747419 0.209146
worst smoothness 0.547691 0.493838
worst compactness 0.801080 0.614441
worst concavity 0.855434 0.532520
worst concave points 1.000000 0.502528
worst symmetry 0.502528 1.000000
worst fractal dimension 0.511114 0.537848
target -0.793566 -0.416294

worst fractal dimension target

mean radius 0.007066 -0.730029
mean texture 0.119205 -0.415185
mean perimeter 0.051019 -0.742636
mean area 0.003738 -0.708984
mean smoothness 0.499316 -0.358560
mean compactness 0.687382 -0.596534
mean concavity 0.514930 -0.696360
mean concave points 0.368661 -0.776614
mean symmetry 0.438413 -0.330499
mean fractal dimension 0.767297 0.012838
radius error 0.049559 -0.567134
texture error -0.045655 0.008303
perimeter error 0.085433 -0.556141
area error 0.017539 -0.548236
smoothness error 0.101480 0.067016
compactness error 0.590973 -0.292999
concavity error 0.439329 -0.253730
concave points error 0.310655 -0.408042
symmetry error 0.078079 0.006522
fractal dimension error 0.591328 -0.077972
worst radius 0.093492 -0.776454
worst texture 0.219122 -0.456903
worst perimeter 0.138957 -0.782914
worst area 0.079647 -0.733825
worst smoothness 0.617624 -0.421465
worst compactness 0.810455 -0.590998
worst concavity 0.686511 -0.659610
worst concave points 0.511114 -0.793566
worst symmetry 0.537848 -0.416294
worst fractal dimension 1.000000 -0.323872
target -0.323872 1.000000

[31 rows x 31 columns]

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 569 entries, 0 to 568
Data columns (total 31 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 mean radius 569 non-null float64
1 mean texture 569 non-null float64
2 mean perimeter 569 non-null float64
3 mean area 569 non-null float64
4 mean smoothness 569 non-null float64
5 mean compactness 569 non-null float64
6 mean concavity 569 non-null float64
7 mean concave points 569 non-null float64
8 mean symmetry 569 non-null float64
9 mean fractal dimension 569 non-null float64
10 radius error 569 non-null float64
11 texture error 569 non-null float64
12 perimeter error 569 non-null float64
 13 area error 569 non-null float64
14 smoothness error 569 non-null float64
15 compactness error 569 non-null float64
16 concavity error 569 non-null float64
17 concave points error 569 non-null float64
18 symmetry error 569 non-null float64
19 fractal dimension error 569 non-null float64
20 worst radius 569 non-null float64
21 worst texture 569 non-null float64
22 worst perimeter 569 non-null float64
23 worst area 569 non-null float64
24 worst smoothness 569 non-null float64
25 worst compactness 569 non-null float64
26 worst concavity 569 non-null float64
27 worst concave points 569 non-null float64
28 worst symmetry 569 non-null float64
29 worst fractal dimension 569 non-null float64
30 target 569 non-null int64
dtypes: float64(30), int64(1)
memory usage: 137.9 KB

sns.heatmap(df.corr(), annot=True, cmap="coolwarm",fmt=".2f")

<Axes: >
x = df.iloc[:, :30].values
y = df.iloc[:, 30].values

from sklearn.preprocessing import StandardScaler

sc = StandardScaler()
x = sc.fit_transform(x)

from sklearn.model_selection import train_test_split

xtrain, xtest, ytrain, ytest = train_test_split(x, y, test_size=0.3,
random_state=1)

ann = Sequential()
ann.add(Dense(units=4, activation="relu"))
ann.add(Dense(units=1, activation="sigmoid")) # Use 'sigmoid' for
binary classification
ann.compile(optimizer="adam", loss="binary_crossentropy")
ann.fit(xtrain, ytrain, batch_size=20, epochs=250)
Epoch 1/250
20/20 [==============================] - 2s 2ms/step - loss: 0.5963
Epoch 2/250
20/20 [==============================] - 0s 2ms/step - loss: 0.5591
Epoch 3/250
20/20 [==============================] - 0s 2ms/step - loss: 0.5320
Epoch 4/250
20/20 [==============================] - 0s 4ms/step - loss: 0.5108
Epoch 5/250
20/20 [==============================] - 0s 3ms/step - loss: 0.4870
Epoch 6/250
20/20 [==============================] - 0s 3ms/step - loss: 0.4578
Epoch 7/250
20/20 [==============================] - 0s 2ms/step - loss: 0.4231
Epoch 8/250
20/20 [==============================] - 0s 2ms/step - loss: 0.3848
Epoch 9/250
20/20 [==============================] - 0s 2ms/step - loss: 0.3477
Epoch 10/250
20/20 [==============================] - 0s 2ms/step - loss: 0.3129
Epoch 11/250
20/20 [==============================] - 0s 3ms/step - loss: 0.2828
Epoch 12/250
20/20 [==============================] - 0s 3ms/step - loss: 0.2571
Epoch 13/250
20/20 [==============================] - 0s 3ms/step - loss: 0.2358
Epoch 14/250
20/20 [==============================] - 0s 2ms/step - loss: 0.2172
Epoch 15/250
20/20 [==============================] - 0s 3ms/step - loss: 0.2021
Epoch 16/250
20/20 [==============================] - 0s 2ms/step - loss: 0.1889
Epoch 17/250
20/20 [==============================] - 0s 2ms/step - loss: 0.1773
Epoch 18/250
20/20 [==============================] - 0s 2ms/step - loss: 0.1670
Epoch 19/250
20/20 [==============================] - 0s 2ms/step - loss: 0.1577
Epoch 20/250
20/20 [==============================] - 0s 3ms/step - loss: 0.1498
Epoch 21/250
20/20 [==============================] - 0s 2ms/step - loss: 0.1423
Epoch 22/250
20/20 [==============================] - 0s 2ms/step - loss: 0.1360
Epoch 23/250
20/20 [==============================] - 0s 2ms/step - loss: 0.1299
Epoch 24/250
20/20 [==============================] - 0s 3ms/step - loss: 0.1246
Epoch 25/250
20/20 [==============================] - 0s 2ms/step - loss: 0.1200
Epoch 26/250
20/20 [==============================] - 0s 2ms/step - loss: 0.1153
Epoch 27/250
20/20 [==============================] - 0s 2ms/step - loss: 0.1111
Epoch 28/250
20/20 [==============================] - 0s 3ms/step - loss: 0.1074
Epoch 29/250
20/20 [==============================] - 0s 2ms/step - loss: 0.1040
Epoch 30/250
20/20 [==============================] - 0s 3ms/step - loss: 0.1008
Epoch 31/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0978
Epoch 32/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0953
Epoch 33/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0929
Epoch 34/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0907
Epoch 35/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0886
Epoch 36/250
20/20 [==============================] - 0s 4ms/step - loss: 0.0868
Epoch 37/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0851
Epoch 38/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0832
Epoch 39/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0820
Epoch 40/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0804
Epoch 41/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0791
Epoch 42/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0778
Epoch 43/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0766
Epoch 44/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0754
Epoch 45/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0744
Epoch 46/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0734
Epoch 47/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0725
Epoch 48/250
20/20 [==============================] - 0s 4ms/step - loss: 0.0717
Epoch 49/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0708
Epoch 50/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0700
Epoch 51/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0692
Epoch 52/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0685
Epoch 53/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0678
Epoch 54/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0672
Epoch 55/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0664
Epoch 56/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0660
Epoch 57/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0653
Epoch 58/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0647
Epoch 59/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0644
Epoch 60/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0637
Epoch 61/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0632
Epoch 62/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0628
Epoch 63/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0623
Epoch 64/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0617
Epoch 65/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0610
Epoch 66/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0605
Epoch 67/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0599
Epoch 68/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0594
Epoch 69/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0589
Epoch 70/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0583
Epoch 71/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0579
Epoch 72/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0575
Epoch 73/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0570
Epoch 74/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0564
Epoch 75/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0561
Epoch 76/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0556
Epoch 77/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0554
Epoch 78/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0549
Epoch 79/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0546
Epoch 80/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0541
Epoch 81/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0538
Epoch 82/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0534
Epoch 83/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0532
Epoch 84/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0527
Epoch 85/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0524
Epoch 86/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0521
Epoch 87/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0517
Epoch 88/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0510
Epoch 89/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0503
Epoch 90/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0494
Epoch 91/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0489
Epoch 92/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0482
Epoch 93/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0474
Epoch 94/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0469
Epoch 95/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0464
Epoch 96/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0459
Epoch 97/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0454
Epoch 98/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0450
Epoch 99/250
20/20 [==============================] - 0s 4ms/step - loss: 0.0448
Epoch 100/250
20/20 [==============================] - 0s 4ms/step - loss: 0.0442
Epoch 101/250
20/20 [==============================] - 0s 4ms/step - loss: 0.0439
Epoch 102/250
20/20 [==============================] - 0s 5ms/step - loss: 0.0436
Epoch 103/250
20/20 [==============================] - 0s 4ms/step - loss: 0.0432
Epoch 104/250
20/20 [==============================] - 0s 4ms/step - loss: 0.0430
Epoch 105/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0426
Epoch 106/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0423
Epoch 107/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0420
Epoch 108/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0417
Epoch 109/250
20/20 [==============================] - 0s 4ms/step - loss: 0.0415
Epoch 110/250
20/20 [==============================] - 0s 4ms/step - loss: 0.0412
Epoch 111/250
20/20 [==============================] - 0s 4ms/step - loss: 0.0409
Epoch 112/250
20/20 [==============================] - 0s 4ms/step - loss: 0.0405
Epoch 113/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0403
Epoch 114/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0398
Epoch 115/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0395
Epoch 116/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0392
Epoch 117/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0389
Epoch 118/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0385
Epoch 119/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0384
Epoch 120/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0379
Epoch 121/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0377
Epoch 122/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0375
Epoch 123/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0370
Epoch 124/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0368
Epoch 125/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0366
Epoch 126/250
20/20 [==============================] - 0s 4ms/step - loss: 0.0362
Epoch 127/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0359
Epoch 128/250
20/20 [==============================] - 0s 4ms/step - loss: 0.0357
Epoch 129/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0353
Epoch 130/250
20/20 [==============================] - 0s 5ms/step - loss: 0.0351
Epoch 131/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0348
Epoch 132/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0347
Epoch 133/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0345
Epoch 134/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0342
Epoch 135/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0339
Epoch 136/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0338
Epoch 137/250
20/20 [==============================] - 0s 4ms/step - loss: 0.0335
Epoch 138/250
20/20 [==============================] - 0s 4ms/step - loss: 0.0332
Epoch 139/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0330
Epoch 140/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0327
Epoch 141/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0326
Epoch 142/250
20/20 [==============================] - 0s 4ms/step - loss: 0.0323
Epoch 143/250
20/20 [==============================] - 0s 4ms/step - loss: 0.0321
Epoch 144/250
20/20 [==============================] - 0s 4ms/step - loss: 0.0319
Epoch 145/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0316
Epoch 146/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0314
Epoch 147/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0313
Epoch 148/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0310
Epoch 149/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0308
Epoch 150/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0305
Epoch 151/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0304
Epoch 152/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0301
Epoch 153/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0299
Epoch 154/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0297
Epoch 155/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0294
Epoch 156/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0293
Epoch 157/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0290
Epoch 158/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0289
Epoch 159/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0286
Epoch 160/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0285
Epoch 161/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0283
Epoch 162/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0281
Epoch 163/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0279
Epoch 164/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0277
Epoch 165/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0275
Epoch 166/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0274
Epoch 167/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0272
Epoch 168/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0271
Epoch 169/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0269
Epoch 170/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0267
Epoch 171/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0265
Epoch 172/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0263
Epoch 173/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0262
Epoch 174/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0260
Epoch 175/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0257
Epoch 176/250
20/20 [==============================] - 0s 4ms/step - loss: 0.0256
Epoch 177/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0255
Epoch 178/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0253
Epoch 179/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0251
Epoch 180/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0250
Epoch 181/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0248
Epoch 182/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0245
Epoch 183/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0244
Epoch 184/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0243
Epoch 185/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0241
Epoch 186/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0240
Epoch 187/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0238
Epoch 188/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0236
Epoch 189/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0235
Epoch 190/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0234
Epoch 191/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0232
Epoch 192/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0230
Epoch 193/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0229
Epoch 194/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0228
Epoch 195/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0225
Epoch 196/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0224
Epoch 197/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0223
Epoch 198/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0222
Epoch 199/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0219
Epoch 200/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0218
Epoch 201/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0217
Epoch 202/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0215
Epoch 203/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0214
Epoch 204/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0212
Epoch 205/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0210
Epoch 206/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0209
Epoch 207/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0207
Epoch 208/250
20/20 [==============================] - 0s 4ms/step - loss: 0.0206
Epoch 209/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0206
Epoch 210/250
20/20 [==============================] - 0s 3ms/step - loss: 0.0204
Epoch 211/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0203
Epoch 212/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0201
Epoch 213/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0199
Epoch 214/250
20/20 [==============================] - 0s 4ms/step - loss: 0.0198
Epoch 215/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0196
Epoch 216/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0195
Epoch 217/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0194
Epoch 218/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0192
Epoch 219/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0191
Epoch 220/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0189
Epoch 221/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0189
Epoch 222/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0187
Epoch 223/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0187
Epoch 224/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0185
Epoch 225/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0183
Epoch 226/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0182
Epoch 227/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0181
Epoch 228/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0179
Epoch 229/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0179
Epoch 230/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0177
Epoch 231/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0176
Epoch 232/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0174
Epoch 233/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0173
Epoch 234/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0172
Epoch 235/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0171
Epoch 236/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0170
Epoch 237/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0168
Epoch 238/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0167
Epoch 239/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0166
Epoch 240/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0165
Epoch 241/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0164
Epoch 242/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0162
Epoch 243/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0163
Epoch 244/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0160
Epoch 245/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0159
Epoch 246/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0158
Epoch 247/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0157
Epoch 248/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0156
Epoch 249/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0155
Epoch 250/250
20/20 [==============================] - 0s 2ms/step - loss: 0.0153

<keras.callbacks.History at 0x788af674f2e0>

# Make predictions on the test set

ypred = ann.predict(xtest)
ypred_class = (ypred > 0.5).astype(int) # Convert probabilities to
binary classes (0 or 1)

6/6 [==============================] - 0s 3ms/step

print(f"Confusion Matrix:\n{confusion_matrix(ytest, ypred_class)}")

Confusion Matrix:
[[ 60 3]
[ 3 105]]

ypred = ann.predict(xtest)
print(f"MSE : {mean_squared_error(ytest, ypred)}")
print(f"RMSE : {np.sqrt(mean_squared_error(ytest,ypred))}")

6/6 [==============================] - 0s 3ms/step

MSE : 0.029022814545983426
RMSE : 0.1703608363033694

# For predicting a new sample, processing steps follow

xnew = [[0.4, 1.2, -0.7, 2.5, -1.0, 0.8, -0.3, 0.6, -0.2, 0.9,
-0.5, 1.1, -0.1, 1.7, -0.4, 0.3, 0.5, 1.0, -0.8, 0.2,
-1.2, 0.6, -0.9, 0.4, -0.6, 1.0, -0.3, 0.7, 1.2, -
0.5]]
xnew = sc.transform(xnew)
yp = ann.predict(xnew)
yp_class = (yp > 0.5).astype(int)
yp_class

1/1 [==============================] - 0s 29ms/step

array([[1]])