/
kaggle6.py
executable file
·173 lines (161 loc) · 6.25 KB
/
kaggle6.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
import matplotlib
matplotlib.use("PS")
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import seaborn as sns
np.random.seed(2)
import itertools
from keras.callbacks import ReduceLROnPlateau
from keras.layers import Conv2D, Dense, Dropout, Flatten, MaxPool2D
from keras.models import Sequential
from keras.optimizers import RMSprop
from keras.preprocessing.image import ImageDataGenerator
from keras.utils.np_utils import to_categorical # convert to one-hot-encoding
from sklearn.metrics import confusion_matrix
from sklearn.model_selection import train_test_split
sns.set(style="white", context="notebook", palette="deep")
train = pd.read_csv("train.csv")
test = pd.read_csv("test.csv")
Y_train = train["label"]
X_train = train.drop(labels=["label"], axis=1)
del train
g = sns.countplot(Y_train)
Y_train.value_counts()
X_train.isnull().any().describe()
test.isnull().any().describe()
X_train = X_train / 255.0
test = test / 255.0
X_train = X_train.values.reshape(-1, 28, 28, 1)
test = test.values.reshape(-1, 28, 28, 1)
Y_train = to_categorical(Y_train, num_classes=10)
random_seed = 2
X_train, X_val, Y_train, Y_val = train_test_split(
X_train, Y_train, test_size=0.1, random_state=random_seed
)
g = plt.imshow(X_train[0][:, :, 0])
model = Sequential()
model.add(
Conv2D(
filters=32,
kernel_size=(5, 5),
padding="Same",
activation="relu",
input_shape=(28, 28, 1),
)
)
model.add(Conv2D(filters=32, kernel_size=(5, 5), padding="Same", activation="relu"))
model.add(MaxPool2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(filters=64, kernel_size=(3, 3), padding="Same", activation="relu"))
model.add(Conv2D(filters=64, kernel_size=(3, 3), padding="Same", activation="relu"))
model.add(MaxPool2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(256, activation="relu"))
model.add(Dropout(0.5))
model.add(Dense(10, activation="softmax"))
optimizer = RMSprop(lr=0.001, rho=0.9, epsilon=1e-08, decay=0.0)
model.compile(
optimizer=optimizer, loss="categorical_crossentropy", metrics=["accuracy"]
)
learning_rate_reduction = ReduceLROnPlateau(
monitor="val_acc", patience=3, verbose=1, factor=0.5, min_lr=0.00001
)
epochs = 1 # Turn epochs to 30 to get 0.9967 accuracy
batch_size = 86
datagen = ImageDataGenerator(
featurewise_center=False, # set input mean to 0 over the dataset
samplewise_center=False, # set each sample mean to 0
featurewise_std_normalization=False, # divide inputs by std of the dataset
samplewise_std_normalization=False, # divide each input by its std
zca_whitening=False, # apply ZCA whitening
rotation_range=10, # randomly rotate images in the range (degrees, 0 to 180)
zoom_range=0.1, # Randomly zoom image
width_shift_range=0.1, # randomly shift images horizontally (fraction of total width)
height_shift_range=0.1, # randomly shift images vertically (fraction of total height)
horizontal_flip=False, # randomly flip images
vertical_flip=False,
) # randomly flip images
datagen.fit(X_train)
history = model.fit_generator(
datagen.flow(X_train, Y_train, batch_size=batch_size),
epochs=epochs,
validation_data=(X_val, Y_val),
verbose=2,
steps_per_epoch=X_train.shape[0] // batch_size,
callbacks=[learning_rate_reduction],
)
fig, ax = plt.subplots(2, 1)
ax[0].plot(history.history["loss"], color="b", label="Training loss")
ax[0].plot(history.history["val_loss"], color="r", label="validation loss", axes=ax[0])
legend = ax[0].legend(loc="best", shadow=True)
ax[1].plot(history.history["acc"], color="b", label="Training accuracy")
ax[1].plot(history.history["val_acc"], color="r", label="Validation accuracy")
legend = ax[1].legend(loc="best", shadow=True)
def plot_confusion_matrix(
cm, classes, normalize=False, title="Confusion matrix", cmap=plt.cm.Blues
):
"""
This function prints and plots the confusion matrix.
Normalization can be applied by setting `normalize=True`.
"""
plt.imshow(cm, interpolation="nearest", cmap=cmap)
plt.title(title)
plt.colorbar()
tick_marks = np.arange(len(classes))
plt.xticks(tick_marks, classes, rotation=45)
plt.yticks(tick_marks, classes)
if normalize:
cm = cm.astype("float") / cm.sum(axis=1)[:, np.newaxis]
thresh = cm.max() / 2.0
for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
plt.text(
j,
i,
cm[i, j],
horizontalalignment="center",
color="white" if cm[i, j] > thresh else "black",
)
plt.tight_layout()
plt.ylabel("True label")
plt.xlabel("Predicted label")
Y_pred = model.predict(X_val)
Y_pred_classes = np.argmax(Y_pred, axis=1)
Y_true = np.argmax(Y_val, axis=1)
confusion_mtx = confusion_matrix(Y_true, Y_pred_classes)
plot_confusion_matrix(confusion_mtx, classes=range(10))
errors = Y_pred_classes - Y_true != 0
Y_pred_classes_errors = Y_pred_classes[errors]
Y_pred_errors = Y_pred[errors]
Y_true_errors = Y_true[errors]
X_val_errors = X_val[errors]
def display_errors(errors_index, img_errors, pred_errors, obs_errors):
"""This function shows 6 images with their predicted and real labels"""
n = 0
nrows = 2
ncols = 3
fig, ax = plt.subplots(nrows, ncols, sharex=True, sharey=True)
for row in range(nrows):
for col in range(ncols):
error = errors_index[n]
ax[row, col].imshow((img_errors[error]).reshape((28, 28)))
ax[row, col].set_title(
"Predicted label :{}\nTrue label :{}".format(
pred_errors[error], obs_errors[error]
)
)
n += 1
Y_pred_errors_prob = np.max(Y_pred_errors, axis=1)
true_prob_errors = np.diagonal(np.take(Y_pred_errors, Y_true_errors, axis=1))
delta_pred_true_errors = Y_pred_errors_prob - true_prob_errors
sorted_dela_errors = np.argsort(delta_pred_true_errors)
most_important_errors = sorted_dela_errors[-6:]
display_errors(
most_important_errors, X_val_errors, Y_pred_classes_errors, Y_true_errors
)
results = model.predict(test)
results = np.argmax(results, axis=1)
results = pd.Series(results, name="Label")
submission = pd.concat([pd.Series(range(1, 28001), name="ImageId"), results], axis=1)
submission.to_csv("cnn_mnist_datagen.csv", index=False)