Spaces:
Runtime error
Runtime error
File size: 15,978 Bytes
d65e24e 9054f9c d65e24e 35ed1d4 923aca9 d65e24e |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 |
# -*- coding: utf-8 -*-
"""Homework04.ipynb
Automatically generated by Colaboratory.
Original file is located at
https://colab.research.google.com/drive/1tbhifsWI51P_52PWIa07jEbXJs136BXr
## **Task 1 (5 points). Prepare the Fashion MNIST dataset**
"""
from tensorflow import keras
fashion_mnist = keras.datasets.fashion_mnist
(X_train_full , y_train_full ),(X_test,y_test) = fashion_mnist.load_data()
X_train_full.shape
X_valid, X_train=X_train_full[:5000] /255.0, X_train_full[5000:] /255.0
y_valid, y_train=y_train_full[:5000],y_train_full[5000:]
X_test=X_test/255.0
X_valid.shape
print("X_train.shape: ", X_train.shape)
print("X_valid.shape: ", X_valid.shape)
print("X_test.shape: ", X_test.shape)
print("y_train.shape: ", y_train.shape)
print("y_valid.shape: ", y_valid.shape)
print("y_test.shape: ", y_test.shape)
"""## **Task 2 (5 points). Visualize the sample images in the training data**"""
class_name=["T-shirt/top","Trouser","Pullover","Dress","Coat","Sandal","Shirt","Sneaker","Bag","Ankle boot"]
class_name[y_train[0]]
import matplotlib as mpl
import matplotlib.pyplot as plt
k=0
n_row = 3
n_col = 3
for i in range(1,n_row*n_col+1):
plt.subplot(n_row, n_col,i)
some_fashion=X_train[i]
plt.imshow(some_fashion, cmap=mpl.cm.binary)
plt.show()
"""## **Task 3 (5 points). Examine the frequency of classes in train, validation, and test set.**"""
import matplotlib.pyplot as plt
plt.figure(figsize=(12,4))
plt.subplot(1,3,1)
plt.hist(y_train,bins=50)
plt.show()
plt.figure(figsize=(12,4))
plt.subplot(1,3,2)
plt.hist(y_valid,bins=50)
plt.show()
plt.figure(figsize=(12,4))
plt.subplot(1,3,3)
plt.hist(y_test,bins=50)
plt.tight_layout
plt.show()
"""## **Task 4: (45 points) Build several classification models**
**Task 4.1.1. (2 points) According to official document of sklearn.neighbors.KNeighborsClassifier, give your own descriptions for the following four parameters about their purpose defined in this function: 'n_neighbors', 'metric', 'p', 'n_jobs'.**
1. n_neighbors-This represents the number of neighbors to be considered to predict.
2. metric-It is the disctance computation one where it calculates the distance between 2 points or neighbours. The default metric is minkowski.
3. n_jobs-This parameter is used to specify how many concurrent processes should be used for routines that are parallelized with joblib .For maximum all CPU's working when its -1 and none as default
4. p-This tells which distance function is used.
**Task 4.1.2. (2 points) According to official document of sklearn.neighbors.KNeighborsClassifier, give your own descriptions for the following four methods about their purpose defined in this function: ‘fit(X,y)’, 'predict(X)', 'predict_proba', 'score(X,y)'.**
1. fit(X,y)-Fit the k-nearest neighbors classifier from the training dataset.
2. predict(X)-Predicts the class label for given data.
3. predict_proba-Gives probability estimates for the test data X.
4. score(X,y)-Gives the mean accuracy on given test data and labels.
**Task 4.1.3: (2 points) Review the steps in Lab05 to build the KNN models.**
"""
img_shape = X_train.shape
n_samples = img_shape[0]
width = img_shape[1]
height = img_shape[2]
X_train_flatten = X_train.reshape(n_samples, width*height)
print("x_train_flatten.shape: ",X_train_flatten.shape)
img_shape1 = X_test.shape
n_samples1 = img_shape1[0]
width1 = img_shape1[1]
height1 = img_shape1[2]
X_test_flatten = X_test.reshape(n_samples1, width1*height1)
print("x_test_flatten.shape: ",X_test_flatten.shape)
img_shape2 = X_valid.shape
n_samples2 = img_shape2[0]
width2 = img_shape2[1]
height2 = img_shape2[2]
X_valid_flatten = X_valid.reshape(n_samples2, width2*height2)
print("x_valid_flatten.shape: ",X_valid_flatten.shape)
from sklearn.neighbors import KNeighborsClassifier
KNN_classifier = KNeighborsClassifier(n_neighbors=3)
KNN_classifier.fit(X_train_flatten, y_train)
y_valid_pred = KNN_classifier.predict(X_valid_flatten)
"""**Task 4.1.4: (2 points) Practice how to save the trained model to disk. Write codes to re-load the model to answer the remaining questions.**
**Task 4.1.5. (2 points) Based on the validation predictions from Task 4.1.3, organize the predicted classes and actual classes into Pandas dataframe as follows:**
"""
import pandas as pd
prediction_summary = pd.DataFrame({'predicted_label':y_valid_pred, 'actual_label':y_valid})
prediction_summary
from sklearn import metrics
print("Accuracy: ", metrics.accuracy_score(y_valid, y_valid_pred))
c=0
for i in range(0,5000):
if(y_valid_pred[i]==y_valid[i]):
c=c+1
print(c)
val_acc=4305/5000
print("Accuracy on validation set is ",val_acc)
"""**Task 4.1.7. (2 points) Calculate the per-class accuracy of the predictions.**"""
frequency = {}
for item in y_valid:
if item in frequency:
frequency[item] += 1
else:
frequency[item] = 1
print(frequency)
class_names = ["T-shirt/top", "Trouser", "Pullover", "Dress", "Coat",
"Sandal", "Shirt", "Sneaker", "Bag", "Ankle boot"]
def get_per_class_accuracy(y, y_pred):
actual_count={'0':0, '1':0, '2':0,'3':0,'4':0,'5':0,'6':0,'7':0,'8':0,'9': 0}
pred_count={'0':0, '1':0, '2':0,'3':0,'4':0,'5':0,'6':0,'7':0,'8':0,'9': 0}
for i in range(5000):
actual_count[str(y[i])]+=1
if y_pred[i]==y[i]:
pred_count[str(y[i])]+=1
t=[]
for i in actual_count.keys():
t.append(pred_count[i]/actual_count[i])
for i in range(10):
print(f'The validation accuracy of {class_names[i]} is : ', t[i], ' ------->', round(t[i]*100,2),"%" )
get_per_class_accuracy(y_valid, y_valid_pred)
"""**Task 4.1.8. (1 points) Let's visualize the classification confusion matrix to check the details of the validation predictions for each class.**"""
import matplotlib.pyplot as plt
from sklearn.metrics import ConfusionMatrixDisplay
ConfusionMatrixDisplay.from_predictions(y_valid, y_valid_pred)
plt.title("Classification Confusion matrix")
plt.show()
"""**Task 4.1.9: (3 points) Try different K values, and select the best model that has highest validation accuracy. Make the predictions on test set (10000 images). And visualize the classification confusion matrix on the test set to report the details of predictions over every class (as Figure in Task 4.1.8).**"""
import time
knn = KNeighborsClassifier(n_neighbors=2)
knn.fit(X_test_flatten,y_test)
start = time.time()
y_test_predicted = knn.predict(X_test_flatten)
end = time.time()
time_duration = end-start
print("Program finishes in {} seconds:".format(time_duration))
ConfusionMatrixDisplay.from_predictions(y_test, y_test_predicted)
plt.title("Classification Confusion matrix")
plt.show()
print("Overall Accuracy = ", metrics.accuracy_score(y_test, y_test_predicted))
knn = KNeighborsClassifier(n_neighbors=4)
knn.fit(X_test_flatten,y_test)
start = time.time()
y_test_predicted = knn.predict(X_test_flatten)
end = time.time()
time_duration = end-start
print("Program finishes in {} seconds:".format(time_duration))
ConfusionMatrixDisplay.from_predictions(y_test, y_test_predicted)
plt.title("Classification Confusion matrix")
plt.show()
print("Overall Accuracy = ", metrics.accuracy_score(y_test, y_test_predicted))
knn = KNeighborsClassifier(n_neighbors=6)
knn.fit(X_test_flatten,y_test)
start = time.time()
y_test_predicted = knn.predict(X_test_flatten)
end = time.time()
time_duration = end-start
print("Program finishes in {} seconds:".format(time_duration))
ConfusionMatrixDisplay.from_predictions(y_test, y_test_predicted)
plt.title("Classification Confusion matrix")
plt.show()
print("Overall Accuracy = ", metrics.accuracy_score(y_test, y_test_predicted))
knn = KNeighborsClassifier(n_neighbors=8)
knn.fit(X_test_flatten,y_test)
start = time.time()
y_test_predicted = knn.predict(X_test_flatten)
end = time.time()
time_duration = end-start
print("Program finishes in {} seconds:".format(time_duration))
ConfusionMatrixDisplay.from_predictions(y_test, y_test_predicted)
plt.title("Classification Confusion matrix")
plt.show()
print("Overall Accuracy = ", metrics.accuracy_score(y_test, y_test_predicted))
knn = KNeighborsClassifier(n_neighbors=10)
knn.fit(X_test_flatten,y_test)
start = time.time()
y_test_predicted = knn.predict(X_test_flatten)
end = time.time()
time_duration = end-start
print("Program finishes in {} seconds:".format(time_duration))
ConfusionMatrixDisplay.from_predictions(y_test, y_test_predicted)
plt.title("Classification Confusion matrix")
plt.show()
print("Overall Accuracy = ", metrics.accuracy_score(y_test, y_test_predicted))
"""**Task 4.1.10: (2 points) Calculate the overall accuracy of the predictions over validation set and test set using the best model from Task 4.1.9.**"""
knn = KNeighborsClassifier(n_neighbors=2)
knn.fit(X_test_flatten,y_test)
y_test_predicted = knn.predict(X_test_flatten)
print("Overall Accuracy of valid set =",metrics.accuracy_score(y_valid,y_valid_pred))
print("Overall Accuracy of test set = ", metrics.accuracy_score(y_test, y_test_predicted))
"""## **(2) (16 points) Task 4.2: Linear discriminant analysis:**
**Task 4.2.1: (4 points) describe how is the bayes classification rule used for multi-class classification?**
The bayes classification is done on bases on bayes theorm. The equation is given as P(class n/ x)=P(x /class n).P(class n)/P(x). We need to calculate
P(class n/x) for all the classes and check which has the highest of all and the prediction goes into the class which has the highest.
**Task 4.2.2: (5 points) Train the model on the training set (55000 images), and report the running time during the prediction process on the validation set (5000 images). Compare the running time with the prediction process of KNN In Task 4.1, which method's prediction is faster?**
"""
import numpy as np
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
clf = LinearDiscriminantAnalysis()
clf.fit(X_train_flatten, y_train)
start = time.time()
predicted_labels = clf.predict(X_valid_flatten)
end = time.time()
time_duration = end-start
print("Program finishes in {} seconds:".format(time_duration))
"""The running time of KNN for validation set is 1.07 seconds whereas it takes 0.025 seconds for Linear Discriminant Analysys. Hence, Linear Discriminant Analysis runs faster for validation set.
**Task 4.2.3: (2 points) Save the trained model to disk. Write codes to re-load the model to answer the remaining questions.**
**Task 4.2.4: (3 points) Calculate the overall accuracy of the predictions over training set, validation set and test set.**
"""
y_test_pred = clf.predict(X_test_flatten)
print("Accuracy of testing Set: ", metrics.accuracy_score(y_test, y_test_pred))
y_valid_pred = clf.predict(X_valid_flatten)
print("Accuracy of validation Set: ", metrics.accuracy_score(y_valid, y_valid_pred))
"""**Task 4.2.5: (2 points) Calculate the per-class accuracy of the predictions over the test set. For instance, among images of T-shirt, we need to calculate how many of T-shirt images are correctly predicted.**"""
get_per_class_accuracy(y_test,y_test_pred)
"""# **(3) (12 points) Task 4.3: Quadratic discriminant analysis:**
**Task 4.3.1: (5 points) Train the model on the training set (55000 images), and report the running time during the prediction process on the validation set (5000 images). Compare the running time with the prediction process of KNN, which method's prediction is faster?**
"""
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis
qda = QuadraticDiscriminantAnalysis()
qda.fit(X_train_flatten, y_train)
start = time.time()
predicted_labels = qda.predict(X_valid_flatten)
end = time.time()
time_duration = end-start
print("Program finishes in {} seconds:".format(time_duration))
"""The running time of KNN for validation set is 1.07 seconds whereas it takes 1.61 seconds for Quadratic Discriminant Analysis. Hence, KNN runs faster for validation set.
**Task 4.3.2: (2 points) Save the trained model to disk. Write codes to re-load the model to answer the remaining questions.**
**Task 4.3.3: (3 points) Calculate the overall accuracy of the predictions over training set, validation set and test set.**
"""
y_train_pred = qda.predict(X_train_flatten)
print("Accuracy of training Set: ", metrics.accuracy_score(y_train, y_train_pred))
y_test_pred = qda.predict(X_test_flatten)
print("Accuracy of testing Set: ", metrics.accuracy_score(y_test, y_test_pred))
y_valid_pred = qda.predict(X_valid_flatten)
print("Accuracy of validating Set: ", metrics.accuracy_score(y_valid, y_valid_pred))
"""**Task 4.3.4: (2 points) Calculate the per-class accuracy of the predictions over the test set. For instance, among images of T-shirt, we need to calculate how many of T-shirt images are correctly predicted.**"""
get_per_class_accuracy(y_test,y_test_pred)
"""# **(3) (12 points) Task 4.4: Gaussian Naive Bayes Classifier**
**Task 4.4.1: (5 points) Train the model on the training set (55000 images), and report the running time during the prediction process on the validation set (5000 images). Compare the running time with the prediction process of KNN, which method's prediction is faster?**
"""
from sklearn.naive_bayes import GaussianNB
gnb = GaussianNB()
gnb.fit(X_train_flatten, y_train)
start = time.time()
predicted_labels = gnb.predict(X_valid_flatten)
end = time.time()
time_duration = end-start
print("Program finishes in {} seconds:".format(time_duration))
"""The running time of KNN for validation set is 1.07 seconds whereas it takes 0.104 seconds for Gaussian Naive Bayes. Hence, Gaussian Naive bayes model runs faster for validation set.
**Task 4.4.2: (2 points) Save the trained model to disk. Write codes to re-load the model to answer the remaining questions.**
**Task 4.4.3: (3 points) Calculate the overall accuracy of the predictions over training set, validation set and test set.**
"""
y_train_pred = gnb.predict(X_train_flatten)
print("Accuracy of training Set: ", metrics.accuracy_score(y_train, y_train_pred))
y_test_pred = gnb.predict(X_test_flatten)
print("Accuracy of testing Set: ", metrics.accuracy_score(y_test, y_test_pred))
y_valid_pred = gnb.predict(X_valid_flatten)
print("Accuracy of validating Set: ", metrics.accuracy_score(y_valid, y_valid_pred))
"""**Task 4.4.4: (2 points) Calculate the per-class accuracy of the predictions over the test set. For instance, among images of T-shirt, we need to calculate how many of T-shirt images are correctly predicted.**"""
get_per_class_accuracy(y_test,y_test_pred)
"""# **Part II (20 points): Deploy the machine learning models on Gradio or huggingface**"""
from gradio.outputs import Label
import gradio as gr
def caption(image,input_module1):
class_names = ["T-shirt/top", "Trouser", "Pullover", "Dress", "Coat",
"Sandal", "Shirt", "Sneaker", "Bag", "Ankle boot"]
image=image.reshape(1,28*28)
if input_module1=="KNN":
output1=KNN_classifier.predict(image)[0]
predictions=KNN_classifier.predict_proba(image)[0]
elif input_module1==("Linear discriminant analysis"):
output1=clf.predict(image)[0]
predictions=clf.predict_proba(image)[0]
elif input_module1==("Quadratic discriminant analysis"):
output1=qda.predict(image)[0]
predictions=qda.predict_proba(image)[0]
elif input_module1=="Naive Bayes classifier":
output1=gnb.predict(image)[0]
predictions=gnb.predict_proba(image)[0]
#print(predictions)
output2 = {}
for i in range(len(predictions)):
output2[class_names[i]] = predictions[i]
return output1 ,output2
input_module = gr.inputs.Image(label = "Input Image",image_mode="L",shape=(28,28))
input_module1 = gr.inputs.Dropdown(choices=["KNN","Linear discriminant analysis", "Quadratic discriminant analysis","Naive Bayes classifier"], label = "Method")
output1 = gr.outputs.Textbox(label = "Predicted Class")
output2=gr.outputs.Label(label= "probability of class")
gr.Interface(fn=caption, inputs=[input_module,input_module1], outputs=[output1,output2]).launch(debug=True)
|