ium_444421/classification.ipynb at c932eb6bbae0fdfd4626f0b85310fa242266dd68

!kaggle datasets download -d yasserh/breast-cancer-dataset

!unzip -o breast-cancer-dataset.zip

import numpy as np
import torch
from torch import nn
from torch.autograd import Variable
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.preprocessing import LabelEncoder
from tensorflow.keras.utils import to_categorical
import torch.nn.functional as F
import pandas as pd

class Model(nn.Module):
    def __init__(self, input_dim):
        super(Model, self).__init__()
        self.layer1 = nn.Linear(input_dim,50)
        self.layer2 = nn.Linear(50, 20)
        self.layer3 = nn.Linear(20, 3)
        
    def forward(self, x):
        x = F.relu(self.layer1(x))
        x = F.relu(self.layer2(x))
        x = F.softmax(self.layer3(x)) # To check with the loss function
        return x

data = pd.read_csv('breast-cancer.csv', index_col=0)
data[1:10]

	diagnosis	radius_mean	texture_mean	perimeter_mean	area_mean	smoothness_mean	compactness_mean	concavity_mean	concave points_mean	symmetry_mean	...	radius_worst	texture_worst	perimeter_worst	area_worst	smoothness_worst	compactness_worst	concavity_worst	concave points_worst	symmetry_worst	fractal_dimension_worst
id
842517	M	20.57	17.77	132.90	1326.0	0.08474	0.07864	0.08690	0.07017	0.1812	...	24.99	23.41	158.80	1956.0	0.1238	0.1866	0.2416	0.1860	0.2750	0.08902
84300903	M	19.69	21.25	130.00	1203.0	0.10960	0.15990	0.19740	0.12790	0.2069	...	23.57	25.53	152.50	1709.0	0.1444	0.4245	0.4504	0.2430	0.3613	0.08758
84348301	M	11.42	20.38	77.58	386.1	0.14250	0.28390	0.24140	0.10520	0.2597	...	14.91	26.50	98.87	567.7	0.2098	0.8663	0.6869	0.2575	0.6638	0.17300
84358402	M	20.29	14.34	135.10	1297.0	0.10030	0.13280	0.19800	0.10430	0.1809	...	22.54	16.67	152.20	1575.0	0.1374	0.2050	0.4000	0.1625	0.2364	0.07678
843786	M	12.45	15.70	82.57	477.1	0.12780	0.17000	0.15780	0.08089	0.2087	...	15.47	23.75	103.40	741.6	0.1791	0.5249	0.5355	0.1741	0.3985	0.12440
844359	M	18.25	19.98	119.60	1040.0	0.09463	0.10900	0.11270	0.07400	0.1794	...	22.88	27.66	153.20	1606.0	0.1442	0.2576	0.3784	0.1932	0.3063	0.08368
84458202	M	13.71	20.83	90.20	577.9	0.11890	0.16450	0.09366	0.05985	0.2196	...	17.06	28.14	110.60	897.0	0.1654	0.3682	0.2678	0.1556	0.3196	0.11510
844981	M	13.00	21.82	87.50	519.8	0.12730	0.19320	0.18590	0.09353	0.2350	...	15.49	30.73	106.20	739.3	0.1703	0.5401	0.5390	0.2060	0.4378	0.10720
84501001	M	12.46	24.04	83.97	475.9	0.11860	0.23960	0.22730	0.08543	0.2030	...	15.09	40.68	97.65	711.4	0.1853	1.0580	1.1050	0.2210	0.4366	0.20750

9 rows × 31 columns

lb = LabelEncoder()
data['diagnosis'] = lb.fit_transform(data['diagnosis'])
features = data.iloc[:, 1:32].values
labels = np.array(data['diagnosis'])

features[1:10]

array([[2.057e+01, 1.777e+01, 1.329e+02, 1.326e+03, 8.474e-02, 7.864e-02,
        8.690e-02, 7.017e-02, 1.812e-01, 5.667e-02, 5.435e-01, 7.339e-01,
        3.398e+00, 7.408e+01, 5.225e-03, 1.308e-02, 1.860e-02, 1.340e-02,
        1.389e-02, 3.532e-03, 2.499e+01, 2.341e+01, 1.588e+02, 1.956e+03,
        1.238e-01, 1.866e-01, 2.416e-01, 1.860e-01, 2.750e-01, 8.902e-02],
       [1.969e+01, 2.125e+01, 1.300e+02, 1.203e+03, 1.096e-01, 1.599e-01,
        1.974e-01, 1.279e-01, 2.069e-01, 5.999e-02, 7.456e-01, 7.869e-01,
        4.585e+00, 9.403e+01, 6.150e-03, 4.006e-02, 3.832e-02, 2.058e-02,
        2.250e-02, 4.571e-03, 2.357e+01, 2.553e+01, 1.525e+02, 1.709e+03,
        1.444e-01, 4.245e-01, 4.504e-01, 2.430e-01, 3.613e-01, 8.758e-02],
       [1.142e+01, 2.038e+01, 7.758e+01, 3.861e+02, 1.425e-01, 2.839e-01,
        2.414e-01, 1.052e-01, 2.597e-01, 9.744e-02, 4.956e-01, 1.156e+00,
        3.445e+00, 2.723e+01, 9.110e-03, 7.458e-02, 5.661e-02, 1.867e-02,
        5.963e-02, 9.208e-03, 1.491e+01, 2.650e+01, 9.887e+01, 5.677e+02,
        2.098e-01, 8.663e-01, 6.869e-01, 2.575e-01, 6.638e-01, 1.730e-01],
       [2.029e+01, 1.434e+01, 1.351e+02, 1.297e+03, 1.003e-01, 1.328e-01,
        1.980e-01, 1.043e-01, 1.809e-01, 5.883e-02, 7.572e-01, 7.813e-01,
        5.438e+00, 9.444e+01, 1.149e-02, 2.461e-02, 5.688e-02, 1.885e-02,
        1.756e-02, 5.115e-03, 2.254e+01, 1.667e+01, 1.522e+02, 1.575e+03,
        1.374e-01, 2.050e-01, 4.000e-01, 1.625e-01, 2.364e-01, 7.678e-02],
       [1.245e+01, 1.570e+01, 8.257e+01, 4.771e+02, 1.278e-01, 1.700e-01,
        1.578e-01, 8.089e-02, 2.087e-01, 7.613e-02, 3.345e-01, 8.902e-01,
        2.217e+00, 2.719e+01, 7.510e-03, 3.345e-02, 3.672e-02, 1.137e-02,
        2.165e-02, 5.082e-03, 1.547e+01, 2.375e+01, 1.034e+02, 7.416e+02,
        1.791e-01, 5.249e-01, 5.355e-01, 1.741e-01, 3.985e-01, 1.244e-01],
       [1.825e+01, 1.998e+01, 1.196e+02, 1.040e+03, 9.463e-02, 1.090e-01,
        1.127e-01, 7.400e-02, 1.794e-01, 5.742e-02, 4.467e-01, 7.732e-01,
        3.180e+00, 5.391e+01, 4.314e-03, 1.382e-02, 2.254e-02, 1.039e-02,
        1.369e-02, 2.179e-03, 2.288e+01, 2.766e+01, 1.532e+02, 1.606e+03,
        1.442e-01, 2.576e-01, 3.784e-01, 1.932e-01, 3.063e-01, 8.368e-02],
       [1.371e+01, 2.083e+01, 9.020e+01, 5.779e+02, 1.189e-01, 1.645e-01,
        9.366e-02, 5.985e-02, 2.196e-01, 7.451e-02, 5.835e-01, 1.377e+00,
        3.856e+00, 5.096e+01, 8.805e-03, 3.029e-02, 2.488e-02, 1.448e-02,
        1.486e-02, 5.412e-03, 1.706e+01, 2.814e+01, 1.106e+02, 8.970e+02,
        1.654e-01, 3.682e-01, 2.678e-01, 1.556e-01, 3.196e-01, 1.151e-01],
       [1.300e+01, 2.182e+01, 8.750e+01, 5.198e+02, 1.273e-01, 1.932e-01,
        1.859e-01, 9.353e-02, 2.350e-01, 7.389e-02, 3.063e-01, 1.002e+00,
        2.406e+00, 2.432e+01, 5.731e-03, 3.502e-02, 3.553e-02, 1.226e-02,
        2.143e-02, 3.749e-03, 1.549e+01, 3.073e+01, 1.062e+02, 7.393e+02,
        1.703e-01, 5.401e-01, 5.390e-01, 2.060e-01, 4.378e-01, 1.072e-01],
       [1.246e+01, 2.404e+01, 8.397e+01, 4.759e+02, 1.186e-01, 2.396e-01,
        2.273e-01, 8.543e-02, 2.030e-01, 8.243e-02, 2.976e-01, 1.599e+00,
        2.039e+00, 2.394e+01, 7.149e-03, 7.217e-02, 7.743e-02, 1.432e-02,
        1.789e-02, 1.008e-02, 1.509e+01, 4.068e+01, 9.765e+01, 7.114e+02,
        1.853e-01, 1.058e+00, 1.105e+00, 2.210e-01, 4.366e-01, 2.075e-01]])

labels[1:10]

array([1, 1, 1, 1, 1, 1, 1, 1, 1])

features_train, features_test, labels_train, labels_test = train_test_split(features, labels, random_state=42, shuffle=True)

# Training
model = Model(features_train.shape[1])
optimizer = torch.optim.Adam(model.parameters(), lr=0.01)
loss_fn = nn.CrossEntropyLoss()
epochs = 100

def print_(loss):
    print ("The loss calculated: ", loss)

# Not using dataloader
x_train, y_train = Variable(torch.from_numpy(features_train)).float(), Variable(torch.from_numpy(labels_train)).long()
for epoch in range(1, epochs+1):
    print ("Epoch #",epoch)
    y_pred = model(x_train)
    loss = loss_fn(y_pred, y_train)
    print_(loss.item())
    
    # Zero gradients
    optimizer.zero_grad()
    loss.backward() # Gradients
    optimizer.step() # Update

Epoch # 1
The loss calculated:  0.922476053237915
Epoch # 2
The loss calculated:  0.9223369359970093
Epoch # 3
The loss calculated:  0.9223369359970093
Epoch # 4
The loss calculated:  0.9223369359970093
Epoch # 5
The loss calculated:  0.9223369359970093
Epoch # 6
The loss calculated:  0.9223369359970093
Epoch # 7
The loss calculated:  0.9223369359970093
Epoch # 8
The loss calculated:  0.9223369359970093
Epoch # 9
The loss calculated:  0.9223369359970093
Epoch # 10
The loss calculated:  0.9223369359970093
Epoch # 11
The loss calculated:  0.9223369359970093
Epoch # 12
The loss calculated:  0.9223369359970093
Epoch # 13
The loss calculated:  0.9223369359970093
Epoch # 14
The loss calculated:  0.9223369359970093
Epoch # 15
The loss calculated:  0.9223369359970093
Epoch # 16
The loss calculated:  0.9223369359970093
Epoch # 17
The loss calculated:  0.9223369359970093
Epoch # 18
The loss calculated:  0.9223369359970093
Epoch # 19
The loss calculated:  0.9223369359970093
Epoch # 20
The loss calculated:  0.9223369359970093
Epoch # 21
The loss calculated:  0.9223369359970093
Epoch # 22
The loss calculated:  0.9223369359970093
Epoch # 23
The loss calculated:  0.9223369359970093
Epoch # 24
The loss calculated:  0.9223369359970093
Epoch # 25
The loss calculated:  0.9223369359970093
Epoch # 26
The loss calculated:  0.9223369359970093
Epoch # 27
The loss calculated:  0.9223369359970093
Epoch # 28
The loss calculated:  0.9223369359970093
Epoch # 29
The loss calculated:  0.9223369359970093
Epoch # 30
The loss calculated:  0.9223369359970093
Epoch # 31
The loss calculated:  0.9223369359970093
Epoch # 32
The loss calculated:  0.9223369359970093
Epoch # 33
The loss calculated:  0.9223369359970093
Epoch # 34
The loss calculated:  0.9223369359970093
Epoch # 35
The loss calculated:  0.9223369359970093
Epoch # 36
The loss calculated:  0.9223369359970093
Epoch # 37
The loss calculated:  0.9223369359970093
Epoch # 38
The loss calculated:  0.9223369359970093
Epoch # 39
The loss calculated:  0.9223369359970093
Epoch # 40
The loss calculated:  0.9223369359970093
Epoch # 41
The loss calculated:  0.9223369359970093
Epoch # 42
The loss calculated:  0.9223369359970093
Epoch # 43
The loss calculated:  0.9223369359970093
Epoch # 44
The loss calculated:  0.9223369359970093
Epoch # 45
The loss calculated:  0.9223369359970093
Epoch # 46
The loss calculated:  0.9223369359970093
Epoch # 47
The loss calculated:  0.9223369359970093
Epoch # 48
The loss calculated:  0.9223369359970093
Epoch # 49
The loss calculated:  0.9223369359970093
Epoch # 50
The loss calculated:  0.9223369359970093
Epoch # 51
The loss calculated:  0.9223369359970093
Epoch # 52
The loss calculated:  0.9223369359970093
Epoch # 53
The loss calculated:  0.9223369359970093
Epoch # 54
The loss calculated:  0.9223369359970093
Epoch # 55
The loss calculated:  0.9223369359970093
Epoch # 56
The loss calculated:  0.9223369359970093
Epoch # 57
The loss calculated:  0.9223369359970093
Epoch # 58
The loss calculated:  0.9223369359970093
Epoch # 59
The loss calculated:  0.9223369359970093
Epoch # 60
The loss calculated:  0.9223369359970093
Epoch # 61
The loss calculated:  0.9223369359970093
Epoch # 62
The loss calculated:  0.9223369359970093
Epoch # 63
The loss calculated:  0.9223369359970093
Epoch # 64
The loss calculated:  0.9223369359970093
Epoch # 65
The loss calculated:  0.9223369359970093
Epoch # 66
The loss calculated:  0.9223369359970093
Epoch # 67
The loss calculated:  0.9223369359970093
Epoch # 68
The loss calculated:  0.9223369359970093
Epoch # 69
The loss calculated:  0.9223369359970093
Epoch # 70
The loss calculated:  0.9223369359970093
Epoch # 71
The loss calculated:  0.9223369359970093
Epoch # 72
The loss calculated:  0.9223369359970093
Epoch # 73
The loss calculated:  0.9223369359970093
Epoch # 74
The loss calculated:  0.9223369359970093
Epoch # 75
The loss calculated:  0.9223369359970093
Epoch # 76
The loss calculated:  0.9223369359970093
Epoch # 77
The loss calculated:  0.9223369359970093
Epoch # 78
The loss calculated:  0.9223369359970093
Epoch # 79
The loss calculated:  0.9223369359970093
Epoch # 80
The loss calculated:  0.9223369359970093
Epoch # 81
The loss calculated:  0.9223369359970093
Epoch # 82
The loss calculated:  0.9223369359970093
Epoch # 83
The loss calculated:  0.9223369359970093
Epoch # 84
The loss calculated:  0.9223369359970093
Epoch # 85
The loss calculated:  0.9223369359970093
Epoch # 86
The loss calculated:  0.9223369359970093
Epoch # 87
The loss calculated:  0.9223369359970093
Epoch # 88
The loss calculated:  0.9223369359970093
Epoch # 89
The loss calculated:  0.9223369359970093
Epoch # 90
The loss calculated:  0.9223369359970093
Epoch # 91
The loss calculated:  0.9223369359970093
Epoch # 92
The loss calculated:  0.9223369359970093
Epoch # 93
The loss calculated:  0.9223369359970093
Epoch # 94
The loss calculated:  0.9223369359970093
Epoch # 95
The loss calculated:  0.9223369359970093
Epoch # 96
The loss calculated:  0.9223369359970093
Epoch # 97
The loss calculated:  0.9223369359970093
Epoch # 98
The loss calculated:  0.9223369359970093
Epoch # 99
The loss calculated:  0.9223369359970093
Epoch # 100
The loss calculated:  0.9223369359970093

/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:11: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
  # This is added back by InteractiveShellApp.init_path()

# Prediction
x_test = Variable(torch.from_numpy(features_test)).float()
pred = model(x_test)

/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:11: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
  # This is added back by InteractiveShellApp.init_path()

pred = pred.detach().numpy()
pred[1:10]

array([[1., 0., 0.],
       [1., 0., 0.],
       [1., 0., 0.],
       [1., 0., 0.],
       [1., 0., 0.],
       [1., 0., 0.],
       [1., 0., 0.],
       [1., 0., 0.],
       [1., 0., 0.]], dtype=float32)

print ("The accuracy is", accuracy_score(labels_test, np.argmax(pred, axis=1)))

The accuracy is 0.6223776223776224

labels_test[0]

torch.save(model, "travel_insurance-pytorch.pkl")

saved_model = torch.load("travel_insurance-pytorch.pkl")

np.argmax(saved_model(x_test[0]).detach().numpy(), axis=0)

/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:11: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
  # This is added back by InteractiveShellApp.init_path()

34 KiB Raw Blame History Unescape Escape

34 KiB

Raw Blame History