Update app.py

app.py

@@ -1,203 +1,3 @@
-fashion_mnist = keras.datasets.fashion_mnist
-(x_train_full, y_train_full), (x_test, y_test) = fashion_mnist.load_data()
-
-x_valid, x_train = x_train_full[:5000], x_train_full[5000:]
-y_valid, y_train = y_train_full[:5000], y_train_full[5000:]
-
-x_train.shape
-import matplotlib as mpl
-import matplotlib.pyplot as plt
-plt.figure(figsize=(14,12))
-
-plt.subplot(3,3,1)
-some_image = x_train[0]
-plt.imshow(some_image, cmap=mpl.cm.binary)
-
-plt.subplot(3,3,2)
-some_image = x_train[1]
-plt.imshow(some_image, cmap=mpl.cm.binary)
-
-plt.subplot(3,3,3)
-some_image = x_train[2]
-plt.imshow(some_image, cmap=mpl.cm.binary)
-
-plt.subplot(3,3,4)
-some_image = x_train[3]
-plt.imshow(some_image, cmap=mpl.cm.binary)
-
-plt.subplot(3,3,5)
-some_image = x_train[4]
-plt.imshow(some_image, cmap=mpl.cm.binary)
-
-plt.subplot(3,3,6)
-some_image = x_train[5]
-plt.imshow(some_image, cmap=mpl.cm.binary)
-
-plt.subplot(3,3,7)
-some_image = x_train[6]
-plt.imshow(some_image, cmap=mpl.cm.binary)
-
-plt.subplot(3,3,8)
-some_image = x_train[7]
-plt.imshow(some_image, cmap=mpl.cm.binary)
-
-plt.subplot(3,3,9)
-some_image = x_train[8]
-plt.imshow(some_image, cmap=mpl.cm.binary)
-
-plt.show()
-
-class_names = ["T-shirt/top","Trouser","Pullover", "Dress","Coat","Sandals","Shirt","Sneaker","Bag","Ankle boot"]
-class_names[y_train[3]]
-
-pd_y_train = pd.DataFrame(y_train)
-
-frequency = pd_y_train.value_counts()
-category = frequency.index.tolist()
-counts = frequency.values.tolist()
-# Visualization of train set
-frequency.plot(kind='bar')
-plt.title ('Bar plot')
-plt.xlabel ('Category')
-plt.ylabel ('Frequency')
-
-img_shape = x_train.shape
-n_samples = img_shape[0]
-width = img_shape[1]
-height = img_shape[2]
-
-print("n_samples: ",n_samples)
-print("width: ",width)
-print("height: ",height)
-
-#flatten each 2d mnist image into 1d array and checing dimensions 
-x_train_flatten = x_train.reshape(n_samples, width*height)
-print("x_train_flatten.shape: ",x_train_flatten.shape)
-from sklearn.preprocessing import StandardScaler
-from sklearn.neighbors import KNeighborsClassifier
-
-# feature scaling
-standardscaler = StandardScaler() 
-X_train_scale = standardscaler.fit_transform(x_train_flatten)
-
-# import KNN classifier from sklearn 
-KNN_classifier_scale = KNeighborsClassifier(n_neighbors=5)
-KNN_classifier_scale. fit(X_train_scale,y_train)
-
-X_test_stand = standardscaler.transform(x_test_flatten)
-y_pred = KNN_classifier_scale.predict(X_test_stand)
-# Cross validation 
-from sklearn.model_selection import cross_val_score
-from sklearn.neighbors import KNeighborsClassifier
-
-# define one KNN model
-KNN_classifier = KNeighborsClassifier(n_neighbors=5, metric = 'euclidean')
-
-# call cross-val_score
-CV_scores = cross_val_score(estimator = KNN_classifier, X = x_train_flatten, y = y_train, cv = 3, scoring = 'accuracy')
-print("CV_scores: ", CV_scores)
-# Training 
-
-from sklearn.model_selection import cross_val_score
-from sklearn.neighbors import KNeighborsClassifier 
-
-import time
-start = time.time()
-
-KNN_classifier = KNeighborsClassifier(n_neighbors=5, metric = 'euclidean')
-KNN_classifier.fit(x_train_flatten, y_train)
-y_valid_predicted_label = KNN_classifier.predict(x_valid_flatten)
-
-end = time.time()
-time_duration = end-start
-print("Program finishes in {} seconds:".format(time_duration))
-# Saving the data
-from joblib import dump, load
-dump(KNN_classifier, 'KNN_fashionmnist.joblib') 
-# loading the data
-KNN_classifier = load('KNN_fashionmnist.joblib')
-
-# organize the predicted classes and actual classes into Pandas dataframe
-summary = pd.DataFrame({'predection':y_valid_predicted_label,'Original':y_valid})
-summary
-
-# Overall accuracy of the validation predictions
-from sklearn import metrics
-metrics.accuracy_score(y_valid,y_valid_predicted_label)
-
-# Calculate the per-class accuracy of the predictions
-from sklearn.metrics import confusion_matrix
-matrix = confusion_matrix(y_valid,y_valid_predicted_label)
-accuracy_score = matrix.diagonal()/matrix.sum(axis=1)
-
-print('accuracy of t-shirt is',accuracy_score[0])
-print('accuracy of Trouser is',accuracy_score[1])
-print('accuracy of pullover is',accuracy_score[2])
-print('accuracy of Dress is',accuracy_score[3])
-print('accuracy of coat is',accuracy_score[4])
-print('accuracy of sandal is',accuracy_score[5])
-print('accuracy of shirt is',accuracy_score[6])
-print('accuracy of sneaker is',accuracy_score[7])
-print('accuracy of bag is',accuracy_score[8])
-print('accuracy of boot is',accuracy_score[9])
-
-# 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_predicted_label)
-plt.title("Classification Confusion matrix")
-plt.show()
-
-# Task 4.1.9 Different K values, and select the best model that has highest validation accuracy
-# visualize the classification confusion matrix on the test set to report the details of predictions over every class
-from sklearn.neighbors import KNeighborsClassifier
-KNN_classifier = KNeighborsClassifier(n_neighbors=3, metric = 'euclidean')
-KNN_classifier.fit(x_train_flatten, y_train)
-y_valid_predicted_label = KNN_classifier.predict(x_valid_flatten)
-
-y_valid_predicted_label
-from sklearn import metrics
-metrics.accuracy_score(y_valid, y_valid_predicted_label)
-
-import matplotlib.pyplot as plt
-from sklearn.metrics import ConfusionMatrixDisplay
-ConfusionMatrixDisplay.from_predictions(y_test, y_test_pred)
-plt.title("classifiaction confusion matrix")
-plt.show()
-# Task 4.1.10: Calculate the overall accuracy of the predictions over  validation set and test set using the best model 
-from sklearn import metrics
-metrics.accuracy_score(y_test, y_test_pred)
-# discriminant analysis
-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))
-
-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))
-
-from sklearn.metrics import confusion_matrix
-matrix = confusion_matrix(y_test,y_test_pred)
-accuracy_score = matrix.diagonal()/matrix.sum(axis=1)
-
-print('accuracy of t-shirt is',accuracy_score[0])
-print('accuracy of Trouser is',accuracy_score[1])
-print('accuracy of pullover is',accuracy_score[2])
-print('accuracy of Dress is',accuracy_score[3])
-print('accuracy of coat is',accuracy_score[4])
-print('accuracy of sandal is',accuracy_score[5])
-print('accuracy of shirt is',accuracy_score[6])
-print('accuracy of sneaker is',accuracy_score[7])
-print('accuracy of bag is',accuracy_score[8])
-print('accuracy of boot is',accuracy_score[9])
 
 from gradio.outputs import Label
 import gradio as gr