├── a.txt ├── cheatsheet.jpg ├── Autoencoder ├── result.png └── Autoencoder.ipynb ├── python basics ├── NUMPY │ ├── 1.py │ ├── 2.py │ ├── 3.py │ ├── 4.py │ ├── version.py │ ├── result1.py │ ├── tofindindexof100thelement.py │ ├── 5.py │ ├── 6.py │ └── NUMPY.ipynb └── .ipynb_checkpoints │ └── NUMPY-checkpoint.ipynb ├── Py and R cheatsheet.jpg ├── Performance Metrics ├── img │ └── auc.png ├── roc_and_auc.md └── metrics in classification.md ├── tensorflow basics ├── autoencoder.png ├── basics1.py ├── basics2.py ├── basics3.py └── autoencoder.py ├── Python for Data Science - cheatsheet.pdf ├── README.md ├── Position_Salaries.csv ├── Cheatsheet by Stanford.md ├── Ensenmble-learning ├── XGBoost.py └── XGBoost_gridSearch.py ├── KNN-ALGORITHM └── KNN.py ├── perceptron ├── perceptron.py ├── perceptronalgo.py └── data.csv ├── prediction.pynb ├── LSTM ├── iris-data.csv └── Untitled1.ipynb ├── LICENSE └── K-means-cluster └── K-MEANS.ipynb /a.txt: -------------------------------------------------------------------------------- 1 | sdasd -------------------------------------------------------------------------------- /cheatsheet.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/somiljain7/AI/HEAD/cheatsheet.jpg -------------------------------------------------------------------------------- /Autoencoder/result.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/somiljain7/AI/HEAD/Autoencoder/result.png -------------------------------------------------------------------------------- /python basics/NUMPY/1.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | z=np.zeros(10) 3 | z[4] = 1 4 | print(z) 5 | -------------------------------------------------------------------------------- /Py and R cheatsheet.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/somiljain7/AI/HEAD/Py and R cheatsheet.jpg -------------------------------------------------------------------------------- /Performance Metrics/img/auc.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/somiljain7/AI/HEAD/Performance Metrics/img/auc.png -------------------------------------------------------------------------------- /python basics/NUMPY/2.py: -------------------------------------------------------------------------------- 1 | #/*randomize in range 10,50 */ 2 | import numpy as np 3 | z=np.arange(10,50) 4 | print(z) 5 | -------------------------------------------------------------------------------- /tensorflow basics/autoencoder.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/somiljain7/AI/HEAD/tensorflow basics/autoencoder.png -------------------------------------------------------------------------------- /python basics/NUMPY/3.py: -------------------------------------------------------------------------------- 1 | #/*REVERSING AN VECTOR*/ 2 | import numpy as np 3 | z=np.arange(50) 4 | z=z[::-1] 5 | print(z) 6 | -------------------------------------------------------------------------------- /python basics/NUMPY/4.py: -------------------------------------------------------------------------------- 1 | #/* CREATING AN 3x3 MATRIX*/ 2 | import numpy as np 3 | z=np.arange(9).reshape(3,3) 4 | print(z) 5 | -------------------------------------------------------------------------------- /python basics/NUMPY/version.py: -------------------------------------------------------------------------------- 1 | import numpy as n 2 | print(n.__version__) 3 | 4 | #to know the version of numpy installed 5 | -------------------------------------------------------------------------------- /Python for Data Science - cheatsheet.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/somiljain7/AI/HEAD/Python for Data Science - cheatsheet.pdf -------------------------------------------------------------------------------- /python basics/NUMPY/result1.py: -------------------------------------------------------------------------------- 1 | import numpy as n 2 | 3 | 0 * n.nan 4 | n.nan == n.nan 5 | n.inf >n.nan 6 | n.nan - n.nan 7 | 0.3 == 3*0.1 8 | -------------------------------------------------------------------------------- /python basics/NUMPY/tofindindexof100thelement.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | print(np.unravel_index(100,(6,7,8))) 3 | 4 | print(np.unravel_index( 5 | -------------------------------------------------------------------------------- /python basics/.ipynb_checkpoints/NUMPY-checkpoint.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [], 3 | "metadata": {}, 4 | "nbformat": 4, 5 | "nbformat_minor": 2 6 | } 7 | -------------------------------------------------------------------------------- /python basics/NUMPY/5.py: -------------------------------------------------------------------------------- 1 | #/* CREATING A CHECKBOARD 8x8 MATRIX*/ 2 | import numpy as np 3 | z=np.tile(np.array([[0,1],[1,0]]),(4,4)) 4 | print(z) 5 | 6 | -------------------------------------------------------------------------------- /python basics/NUMPY/6.py: -------------------------------------------------------------------------------- 1 | 2 | #/* NORMALIZING 5x5 MATRIX*/ 3 | import numpy as np 4 | Z=np.random.random((5,5)) 5 | Zmax,Zmin = Z.max(),Z.min() 6 | Z = (Z - Zmin)/(Zmax - Zmin) 7 | print(Z) 8 | 9 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # ` AI ALGORITHMS ` 2 | **This repository contains my algorithm implemetantion +EDA + data visualization** 3 | 4 | # `Setup: ` 5 | ``` 6 | $ git clone https://github.com/somiljain7/AI.git 7 | 8 | ``` 9 | # `feel free to contribute :)` 10 | 11 | 12 | 13 | -------------------------------------------------------------------------------- /tensorflow basics/basics1.py: -------------------------------------------------------------------------------- 1 | import tensorflow as tf 2 | from tensorflow.keras import Sequential 3 | from tensorflow.keras.layers import Dense 4 | 5 | model = Sequential() 6 | model.add(Dense(3, input_dim=2 ,activation='relu')) 7 | model.add(Dense(1, activation='softmax')) 8 | 9 | -------------------------------------------------------------------------------- /Position_Salaries.csv: -------------------------------------------------------------------------------- 1 | Position,Level,Salary 2 | Business Analyst,1,45000 3 | Junior Consultant,2,50000 4 | Senior Consultant,3,60000 5 | Manager,4,80000 6 | Country Manager,5,110000 7 | Region Manager,6,150000 8 | Partner,7,200000 9 | Senior Partner,8,300000 10 | C-level,9,500000 11 | CEO,10,1000000 -------------------------------------------------------------------------------- /Cheatsheet by Stanford.md: -------------------------------------------------------------------------------- 1 | ### Machine Learning Cheatsheet by Stanford University 2 | 3 | ### For Classification and Regression Metrics 4 | https://stanford.edu/~shervine/teaching/cs-229/cheatsheet-machine-learning-tips-and-tricks 5 | 6 | ### For Supervised Learning 7 | https://stanford.edu/~shervine/teaching/cs-229/cheatsheet-supervised-learning 8 | 9 | ### For Unsupervised Learning 10 | https://stanford.edu/~shervine/teaching/cs-229/cheatsheet-unsupervised-learning 11 | -------------------------------------------------------------------------------- /Ensenmble-learning/XGBoost.py: -------------------------------------------------------------------------------- 1 | import xgboost as xgb 2 | 3 | #Using the XGBoost Classifier. I have used just a few combinations here and there without GridSearch or RandomSearch because the dataset was pretty small 4 | xg_cl = xgb.XGBClassifier(objective='binary:logistic', n_estimators=500,seed=42,learning_rate=0.01,max_depth=5,colsample_bytree=0.75,subsample=0.7, 5 | tree_method='exact', min_child_weight=4,reg_alpha=0.005) 6 | 7 | #fitting the model 8 | xg_cl.fit(X_train,y_train) 9 | -------------------------------------------------------------------------------- /tensorflow basics/basics2.py: -------------------------------------------------------------------------------- 1 | import tensorflow as tf 2 | from tensorflow.keras import Model 3 | from tensorflow.keras.layers import Dense 4 | 5 | class SimpleNeuralNetwork(Model): 6 | def __init__(self): 7 | super(SimpleNeuralNetwork , self).__init__() 8 | self.layer1 = Dense(2,activation='relu') 9 | self.layer2 = Dense(3,activation='relu') 10 | self.outputLayer = Dense(1,activation='softmax') 11 | def call(self, x): 12 | x = self.layer1(x) 13 | x = self.layer2(x) 14 | return self.outputLayer(x) 15 | 16 | Model = SimpleNeuralNetwork() 17 | 18 | 19 | -------------------------------------------------------------------------------- /KNN-ALGORITHM/KNN.py: -------------------------------------------------------------------------------- 1 | import tensorflow as tf 2 | import numpy as np 3 | from scipy import stats 4 | from tensorflow.examples.tutorials.mnist import input_data 5 | 6 | mnist = input_data.read_data_sets("/tmp/data/", one_hot=True) 7 | X_train,y_train = mnist.train.next_batch(5000) 8 | X_test, y_test = mnist.test.next_batch(100) 9 | k=3 10 | target_x= tf.placeholder("float",[1784]) 11 | X = tf.placeholder("float",[None, 784]) 12 | y = tf.placeholder("float",[None, 10]) 13 | l1_dist = tf.reduce_sum(tf.abs(tf.sub(x, target_x)), 1) 14 | l2_dist = tf.reduce_sum(tf.square(tf.sub(x, target_x)), 1) 15 | nn = tf.nn.top_k(-l1_dist, k) 16 | init = tf.initialize_all_variables() 17 | accuracy_history = [] 18 | with tf.Session() as sess: 19 | sess.run(init) 20 | -------------------------------------------------------------------------------- /Performance Metrics/roc_and_auc.md: -------------------------------------------------------------------------------- 1 | ## ROC and AUC 2 | 3 | refer: 4 | - https://www.youtube.com/watch?v=A_ZKMsZ3f3o 5 | - https://developers.google.com/machine-learning/crash-course/classification/roc-and-auc 6 | 7 | **Receiver operating characteristic curve (ROC)** 8 | Receiver operating characteristic curve, performance of classification model at all threshold 9 | - T+ve and F+ve 10 | 11 | 12 | 13 | **Area under the curve (AUC)** 14 | 1. condiser some threshold value 15 | 2. Find output y^ for all threshold values 16 | 3. calculate True+ve and False+ve 17 | 4. Plot a graph F+ve vs T+ve 18 | 19 | - AUC dir proportional to area 20 | - Model should be always greater than linear line in graph 21 | - Focus on True Positive values 22 | - Select the best threshold value 23 | 24 | ![AUC](img/auc.png) 25 | -------------------------------------------------------------------------------- /Ensenmble-learning/XGBoost_gridSearch.py: -------------------------------------------------------------------------------- 1 | from xgboost.sklearn import XGBRegressor 2 | import datetime 3 | from sklearn.model_selection import GridSearchCV 4 | 5 | # Various hyper-parameters to tune 6 | xgb1 = XGBRegressor() 7 | parameters = {'nthread':[4], #when use hyperthread, xgboost may become slower 8 | 'objective':['reg:linear'], 9 | 'learning_rate': [.03, 0.05, .07, .01, 0.1], #so called `eta` value 10 | 'max_depth': [5, 6, 7], 11 | 'min_child_weight': [4, 3, 2], 12 | 'silent': [1], 13 | 'subsample': [0.7, 0.75, 0.8], 14 | 'colsample_bytree': [0.7, 0.75, 0.8], 15 | 'n_estimators': [500, 600, 700, 800, 900, 1000]} 16 | 17 | xgb_grid = GridSearchCV(xgb1, parameters, cv = 2, n_jobs = 5, verbose=True) 18 | 19 | xgb_grid.fit(X_train, y_train) 20 | 21 | print(xgb_grid.best_score_) 22 | print(xgb_grid.best_params_) 23 | 24 | preds = xg_cl.predict(X_test) 25 | -------------------------------------------------------------------------------- /perceptron/perceptron.py: -------------------------------------------------------------------------------- 1 | import pandas as pd 2 | 3 | # TODO: Set weight1, weight2, and bias 4 | weight1 = 1.5 5 | weight2 = 1.5 6 | bias = -2.0 7 | 8 | 9 | # DON'T CHANGE ANYTHING BELOW 10 | # Inputs and outputs 11 | test_inputs = [(0, 0), (0, 1), (1, 0), (1, 1)] 12 | correct_outputs = [False, False, False, True] 13 | outputs = [] 14 | 15 | # Generate and check output 16 | for test_input, correct_output in zip(test_inputs, correct_outputs): 17 | linear_combination = weight1 * test_input[0] + weight2 * test_input[1] + bias 18 | output = int(linear_combination >= 0) 19 | is_correct_string = 'Yes' if output == correct_output else 'No' 20 | outputs.append([test_input[0], test_input[1], linear_combination, output, is_correct_string]) 21 | 22 | # Print output 23 | num_wrong = len([output[4] for output in outputs if output[4] == 'No']) 24 | output_frame = pd.DataFrame(outputs, columns=['Input 1', ' Input 2', ' Linear Combination', ' Activation Output', ' Is Correct']) 25 | if not num_wrong: 26 | print('Nice! You got it all correct.\n') 27 | else: 28 | print('You got {} wrong. Keep trying!\n'.format(num_wrong)) 29 | print(output_frame.to_string(index=False)) -------------------------------------------------------------------------------- /prediction.pynb: -------------------------------------------------------------------------------- 1 | import pandas as pd 2 | import seaborn as sns 3 | import matplotlib.pyplot as plt 4 | from sklearn.ensemble import RandomForestClassifier 5 | from sklearn.svm import SVC 6 | from sklearn.linear_model import SGDClassifier 7 | from sklearn.metrics import confusion_matrix, classification_report 8 | from sklearn.preprocessing import StandardScaler, LabelEncoder 9 | from sklearn.model_selection import train_test_split, GridSearchCV, cross_val_score 10 | %matplotlib inline 11 | 12 | #Loading dataset 13 | wine = pd.read_csv('../input/winequality-red.csv') 14 | wine.head() 15 | 16 | 17 | 18 | #Now seperate the dataset as response variable and feature variabes 19 | X = wine.drop('quality', axis = 1) 20 | y = wine['quality'] 21 | 22 | X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 42) 23 | 24 | 25 | 26 | 27 | #Applying Standard scaling to get optimized result 28 | sc = StandardScaler() 29 | 30 | 31 | 32 | X_train = sc.fit_transform(X_train) 33 | X_test = sc.fit_transform(X_test) 34 | 35 | svc2 = SVC(C = 1.2, gamma = 0.9, kernel= 'rbf') 36 | svc2.fit(X_train, y_train) 37 | pred_svc2 = svc2.predict(X_test) 38 | print(classification_report(y_test, pred_svc2)) 39 | 40 | 41 | -------------------------------------------------------------------------------- /tensorflow basics/basics3.py: -------------------------------------------------------------------------------- 1 | import quandl 2 | import numpy as np 3 | from sklearn.linear_model import LinearRegression 4 | from sklearn.svm import SVR 5 | from sklearn.model_selection import train_test_split 6 | # Get the stock data 7 | df = quandl.get("WIKI/AMZN") 8 | # Take a look at the data 9 | # Get the Adjusted Close Price 10 | df = df[['Adj. Close']] 11 | # A variable for predicting 'n' days out into the future 12 | forecast_out = 30 #'n=30' days 13 | #Create another column (the target ) shifted 'n' units up 14 | df['Prediction'] = df[['Adj. Close']].shift(-forecast_out) 15 | #print the new data set 16 | print(df.tail()) 17 | X = np.array(df.drop(['Prediction'],1)) 18 | 19 | #Remove the last '30' rows 20 | X = X[:-forecast_out] 21 | print(X) 22 | ### Create the dependent data set (y) ##### 23 | # Convert the dataframe to a numpy array 24 | y = np.array(df['Prediction']) 25 | # Get all of the y values except the last '30' rows 26 | y = y[:-forecast_out] 27 | print(y) 28 | # Split the data into 80% training and 20% testing 29 | x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2) 30 | # Create and train the Support Vector Machine (Regressor) 31 | svr_rbf = SVR(kernel='rbf', C=1e3, gamma=0.1) 32 | svr_rbf.fit(x_train, y_train) 33 | 34 | -------------------------------------------------------------------------------- /Performance Metrics/metrics in classification.md: -------------------------------------------------------------------------------- 1 | ## All Metrics in Classification 2 | 3 | **Classification Problem** 4 | Default threshold in `0.5` 5 | - Class Labels 6 | - Probabilities (AUC, ROC, PR Curve) 7 | 8 | **Dataset (based on labels)** 9 | - Nearly equal number of records for both labels => `Accuracy` 10 | - Unequal records for labels => Recall, Precision, Fß (F1 Score) and `not Accuracy` 11 | 12 | 1. Confusion Matrix 13 | 2x2 matrix 14 | - top (Actual Values) 15 | - left Predicted Values 16 | 17 | ![Confusion Matrix](https://miro.medium.com/max/712/1*Z54JgbS4DUwWSknhDCvNTQ.png) 18 | 19 | - False +ve => Type 1 Error 20 | - False -ve => Type 2 Error 21 | 22 | Aim - 23 | - Reducing Type1 and Type2 Error 24 | - Accurate values T+ve and T-ve 25 | 26 | **Parameters** 27 | - Balanced Dataset 28 | 29 | Accuracy = (TP + TN) / (TP + FP + FN + TN) 30 | 31 | - Imbalanced Dataset 32 | 33 | Recall(True +ve Rate or Sensitivity) = Out of all +ve values , how many +ve correctly predicted 34 | 35 | Precision(+ve Pred value) = Out of all actual predicted result, how many actual +ve 36 | 37 | ![Recall Precision](https://miro.medium.com/max/888/1*7J08ekAwupLBegeUI8muHA.png) 38 | 39 | 40 | 2. Fß Score - To reduce type 1 and type 2 errors 41 | 42 | ![Fß Score](https://miro.medium.com/max/1092/1*2YIU9iAzaE_g91vv2XU7Ew.png) 43 | 44 | when ß = 1 => Harmonic mean 45 | - When F+ve and F-ve is important then ß = 1 46 | - Type 1 error ß > 1 47 | - Type 2 error ß = 0.5 to 1 mostly 0.5 48 | -------------------------------------------------------------------------------- /perceptron/perceptronalgo.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | # Setting the random seed, feel free to change it and see different solutions. 3 | np.random.seed(42) 4 | 5 | def stepFunction(t): 6 | if t >= 0: 7 | return 1 8 | return 0 9 | 10 | def prediction(X, W, b): 11 | return stepFunction((np.matmul(X,W)+b)[0]) 12 | 13 | # TODO: Fill in the code below to implement the perceptron trick. 14 | # The function should receive as inputs the data X, the labels y, 15 | # the weights W (as an array), and the bias b, 16 | # update the weights and bias W, b, according to the perceptron algorithm, 17 | # and return W and b. 18 | def perceptronStep(X, y, W, b, learn_rate = 0.01): 19 | for i in range(len(X)): 20 | y_hat = prediction(X[i],W,b) 21 | if y[i]-y_hat == 1: 22 | W[0] += X[i][0]*learn_rate 23 | W[1] += X[i][1]*learn_rate 24 | b += learn_rate 25 | elif y[i]-y_hat == -1: 26 | W[0] -= X[i][0]*learn_rate 27 | W[1] -= X[i][1]*learn_rate 28 | b -= learn_rate 29 | return W, b 30 | 31 | 32 | # This function runs the perceptron algorithm repeatedly on the dataset, 33 | # and returns a few of the boundary lines obtained in the iterations, 34 | # for plotting purposes. 35 | # Feel free to play with the learning rate and the num_epochs, 36 | # and see your results plotted below. 37 | def trainPerceptronAlgorithm(X, y, learn_rate = 0.01, num_epochs = 25): 38 | x_min, x_max = min(X.T[0]), max(X.T[0]) 39 | y_min, y_max = min(X.T[1]), max(X.T[1]) 40 | W = np.array(np.random.rand(2,1)) 41 | b = np.random.rand(1)[0] + x_max 42 | # These are the solution lines that get plotted below. 43 | boundary_lines = [] 44 | for i in range(num_epochs): 45 | # In each epoch, we apply the perceptron step. 46 | W, b = perceptronStep(X, y, W, b, learn_rate) 47 | boundary_lines.append((-W[0]/W[1], -b/W[1])) 48 | return boundary_lines 49 | -------------------------------------------------------------------------------- /perceptron/data.csv: -------------------------------------------------------------------------------- 1 | 0.78051,-0.063669,1 2 | 0.28774,0.29139,1 3 | 0.40714,0.17878,1 4 | 0.2923,0.4217,1 5 | 0.50922,0.35256,1 6 | 0.27785,0.10802,1 7 | 0.27527,0.33223,1 8 | 0.43999,0.31245,1 9 | 0.33557,0.42984,1 10 | 0.23448,0.24986,1 11 | 0.0084492,0.13658,1 12 | 0.12419,0.33595,1 13 | 0.25644,0.42624,1 14 | 0.4591,0.40426,1 15 | 0.44547,0.45117,1 16 | 0.42218,0.20118,1 17 | 0.49563,0.21445,1 18 | 0.30848,0.24306,1 19 | 0.39707,0.44438,1 20 | 0.32945,0.39217,1 21 | 0.40739,0.40271,1 22 | 0.3106,0.50702,1 23 | 0.49638,0.45384,1 24 | 0.10073,0.32053,1 25 | 0.69907,0.37307,1 26 | 0.29767,0.69648,1 27 | 0.15099,0.57341,1 28 | 0.16427,0.27759,1 29 | 0.33259,0.055964,1 30 | 0.53741,0.28637,1 31 | 0.19503,0.36879,1 32 | 0.40278,0.035148,1 33 | 0.21296,0.55169,1 34 | 0.48447,0.56991,1 35 | 0.25476,0.34596,1 36 | 0.21726,0.28641,1 37 | 0.67078,0.46538,1 38 | 0.3815,0.4622,1 39 | 0.53838,0.32774,1 40 | 0.4849,0.26071,1 41 | 0.37095,0.38809,1 42 | 0.54527,0.63911,1 43 | 0.32149,0.12007,1 44 | 0.42216,0.61666,1 45 | 0.10194,0.060408,1 46 | 0.15254,0.2168,1 47 | 0.45558,0.43769,1 48 | 0.28488,0.52142,1 49 | 0.27633,0.21264,1 50 | 0.39748,0.31902,1 51 | 0.5533,1,0 52 | 0.44274,0.59205,0 53 | 0.85176,0.6612,0 54 | 0.60436,0.86605,0 55 | 0.68243,0.48301,0 56 | 1,0.76815,0 57 | 0.72989,0.8107,0 58 | 0.67377,0.77975,0 59 | 0.78761,0.58177,0 60 | 0.71442,0.7668,0 61 | 0.49379,0.54226,0 62 | 0.78974,0.74233,0 63 | 0.67905,0.60921,0 64 | 0.6642,0.72519,0 65 | 0.79396,0.56789,0 66 | 0.70758,0.76022,0 67 | 0.59421,0.61857,0 68 | 0.49364,0.56224,0 69 | 0.77707,0.35025,0 70 | 0.79785,0.76921,0 71 | 0.70876,0.96764,0 72 | 0.69176,0.60865,0 73 | 0.66408,0.92075,0 74 | 0.65973,0.66666,0 75 | 0.64574,0.56845,0 76 | 0.89639,0.7085,0 77 | 0.85476,0.63167,0 78 | 0.62091,0.80424,0 79 | 0.79057,0.56108,0 80 | 0.58935,0.71582,0 81 | 0.56846,0.7406,0 82 | 0.65912,0.71548,0 83 | 0.70938,0.74041,0 84 | 0.59154,0.62927,0 85 | 0.45829,0.4641,0 86 | 0.79982,0.74847,0 87 | 0.60974,0.54757,0 88 | 0.68127,0.86985,0 89 | 0.76694,0.64736,0 90 | 0.69048,0.83058,0 91 | 0.68122,0.96541,0 92 | 0.73229,0.64245,0 93 | 0.76145,0.60138,0 94 | 0.58985,0.86955,0 95 | 0.73145,0.74516,0 96 | 0.77029,0.7014,0 97 | 0.73156,0.71782,0 98 | 0.44556,0.57991,0 99 | 0.85275,0.85987,0 100 | 0.51912,0.62359,0 101 | -------------------------------------------------------------------------------- /tensorflow basics/autoencoder.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | import keras 3 | from keras.layers import Input, Dense, Conv2D, MaxPooling2D, UpSampling2D 4 | from keras.models import Model 5 | from sklearn.model_selection import train_test_split 6 | import matplotlib.pyplot as plt 7 | (X_train, _), (X_test, _) = keras.datasets.mnist.load_data() 8 | X_train[0].shape 9 | plt.figure(figsize=(10,5)) 10 | for i in range(10): 11 | plt.subplot(1, 10, i+1) 12 | plt.imshow(X_train[i], cmap='gray') 13 | plt.xticks([]) 14 | plt.yticks([]) 15 | plt.show() 16 | inputs =Input(shape=(784,)) 17 | enc = Dense(32,activation='relu') #compressing using 32 neurons 18 | encoded = enc(inputs) 19 | dec = Dense(784,activation='sigmoid')# decompress to 784 pixel 20 | decoded = dec(encoded) 21 | autoencoder = Model(inputs, decoded) 22 | autoencoder.compile(optimizer='adam', loss='binary_crossentropy') 23 | def preprocess(x): 24 | x = x.astype('float32') / 255. 25 | return x.reshape(-1, np.prod(x.shape[1:])) # flatten 26 | 27 | X_train = preprocess(X_train) 28 | X_test = preprocess(X_test) 29 | 30 | # a validation set for training 31 | X_train, X_valid = train_test_split(X_train, test_size=500) 32 | autoencoder.fit(X_train, X_train, epochs=50, batch_size=128, validation_data=(X_valid, X_valid)) 33 | encoder = Model(inputs, encoded) 34 | X_test_encoded = encoder.predict(X_test) 35 | X_test_encoded[0].shape 36 | decoder_inputs = Input(shape=(32,)) 37 | decoder = Model(decoder_inputs, dec(decoder_inputs)) 38 | X_test_decoded = decoder.predict(X_test_encoded) 39 | def show_images(before_images, after_images): 40 | plt.figure(figsize=(10, 2)) 41 | for i in range(10): 42 | # before 43 | plt.subplot(2, 10, i+1) 44 | plt.imshow(before_images[i].reshape(28, 28), cmap='gray') 45 | plt.xticks([]) 46 | plt.yticks([]) 47 | # after 48 | plt.subplot(2, 10, 10+i+1) 49 | plt.imshow(after_images[i].reshape(28, 28), cmap='gray') 50 | plt.xticks([]) 51 | plt.yticks([]) 52 | plt.show() 53 | 54 | show_images(X_test, X_test_decoded) 55 | #Convolutional Autoencoder ka function 56 | def convauto():# encoding 57 | inputs = Input(shape=(28, 28, 1)) 58 | x = Conv2D(16, 3, activation='relu', padding='same')(inputs) 59 | x = MaxPooling2D(padding='same')(x) 60 | x = Conv2D( 8, 3, activation='relu', padding='same')(x) 61 | x = MaxPooling2D(padding='same')(x) 62 | x = Conv2D( 8, 3, activation='relu', padding='same')(x) 63 | encoded = MaxPooling2D(padding='same')(x) 64 | 65 | # decoding 66 | x = Conv2D( 8, 3, activation='relu', padding='same')(encoded) 67 | x = UpSampling2D()(x) 68 | x = Conv2D( 8, 3, activation='relu', padding='same')(x) 69 | x = UpSampling2D()(x) 70 | x = Conv2D(16, 3, activation='relu')(x) 71 | x = UpSampling2D()(x) 72 | decoded = Conv2D(1, 3, activation='sigmoid', padding='same')(x) 73 | 74 | # autoencoder 75 | autoencoder = Model(inputs, decoded) 76 | autoencoder.compile(optimizer='adam', loss='binary_crossentropy') 77 | return autoencoder 78 | 79 | autoencoder = convauto() 80 | autoencoder.summary() 81 | 82 | X_train = X_train.reshape(-1, 28, 28, 1) 83 | X_valid = X_valid.reshape(-1, 28, 28, 1) 84 | X_test = X_test.reshape(-1, 28, 28, 1) 85 | 86 | autoencoder.fit(X_train, X_train, epochs=50, batch_size=128, validation_data=(X_valid, X_valid)) 87 | X_test_dec = autoencoder.predict(X_test) 88 | 89 | show_images(X_test, X_test_dec) 90 | 91 | 92 | def add_noise(x, noise_factor=0.2): 93 | x = x + np.random.randn(*x.shape) * noise_factor 94 | x = x.clip(0., 1.) 95 | return x 96 | 97 | X_train_noisy = add_noise(X_train) 98 | X_valid_noisy = add_noise(X_valid) 99 | X_test_noisy = add_noise(X_test) 100 | 101 | autoencoder = convauto() 102 | autoencoder.fit(X_train_noisy, X_train, epochs=50, batch_size=128, validation_data=(X_valid_noisy, X_valid)) 103 | X_test_dec = autoencoder.predict(X_test_noisy) 104 | 105 | show_images(X_test_noisy, X_test_dec) -------------------------------------------------------------------------------- /LSTM/iris-data.csv: -------------------------------------------------------------------------------- 1 | sepal_length_cm,sepal_width_cm,petal_length_cm,petal_width_cm,class 5.1,3.5,1.4,0.2,Iris-setosa 4.9,3,1.4,0.2,Iris-setosa 4.7,3.2,1.3,0.2,Iris-setosa 4.6,3.1,1.5,0.2,Iris-setosa 5,3.6,1.4,0.2,Iris-setosa 5.4,3.9,1.7,0.4,Iris-setosa 4.6,3.4,1.4,0.3,Iris-setosa 5,3.4,1.5,NA,Iris-setosa 4.4,2.9,1.4,NA,Iris-setosa 4.9,3.1,1.5,NA,Iris-setosa 5.4,3.7,1.5,NA,Iris-setosa 4.8,3.4,1.6,NA,Iris-setosa 4.8,3,1.4,0.1,Iris-setosa 5.7,3,1.1,0.1,Iris-setosa 5.8,4,1.2,0.2,Iris-setosa 5.7,4.4,1.5,0.4,Iris-setosa 5.4,3.9,1.3,0.4,Iris-setosa 5.1,3.5,1.4,0.3,Iris-setosa 5.7,3.8,1.7,0.3,Iris-setossa 5.1,3.8,1.5,0.3,Iris-setosa 5.4,3.4,1.7,0.2,Iris-setosa 5.1,3.7,1.5,0.4,Iris-setosa 4.6,3.6,1,0.2,Iris-setosa 5.1,3.3,1.7,0.5,Iris-setosa 4.8,3.4,1.9,0.2,Iris-setosa 5,3,1.6,0.2,Iris-setosa 5,3.4,1.6,0.4,Iris-setosa 5.2,3.5,1.5,0.2,Iris-setosa 5.2,3.4,1.4,0.2,Iris-setosa 4.7,3.2,1.6,0.2,Iris-setosa 4.8,3.1,1.6,0.2,Iris-setosa 5.4,3.4,1.5,0.4,Iris-setosa 5.2,4.1,1.5,0.1,Iris-setosa 5.5,4.2,1.4,0.2,Iris-setosa 4.9,3.1,1.5,0.1,Iris-setosa 5,3.2,1.2,0.2,Iris-setosa 5.5,3.5,1.3,0.2,Iris-setosa 4.9,3.1,1.5,0.1,Iris-setosa 4.4,3,1.3,0.2,Iris-setosa 5.1,3.4,1.5,0.2,Iris-setosa 5,3.5,1.3,0.3,Iris-setosa 4.5,2.3,1.3,0.3,Iris-setosa 4.4,3.2,1.3,0.2,Iris-setosa 5,3.5,1.6,0.6,Iris-setosa 5.1,3.8,1.9,0.4,Iris-setosa 4.8,3,1.4,0.3,Iris-setosa 5.1,3.8,1.6,0.2,Iris-setosa 4.6,3.2,1.4,0.2,Iris-setosa 5.3,3.7,1.5,0.2,Iris-setosa 5,3.3,1.4,0.2,Iris-setosa 7,3.2,4.7,1.4,Iris-versicolor 6.4,3.2,4.5,1.5,Iris-versicolor 6.9,3.1,4.9,1.5,Iris-versicolor 5.5,2.3,4,1.3,Iris-versicolor 6.5,2.8,4.6,1.5,Iris-versicolor 5.7,2.8,4.5,1.3,Iris-versicolor 6.3,3.3,4.7,1.6,Iris-versicolor 4.9,2.4,3.3,1,Iris-versicolor 6.6,2.9,4.6,1.3,Iris-versicolor 5.2,2.7,3.9,1.4,Iris-versicolor 5,2,3.5,1,Iris-versicolor 5.9,3,4.2,1.5,Iris-versicolor 6,2.2,4,1,Iris-versicolor 6.1,2.9,4.7,1.4,Iris-versicolor 5.6,2.9,3.6,1.3,Iris-versicolor 6.7,3.1,4.4,1.4,Iris-versicolor 5.6,3,4.5,1.5,Iris-versicolor 5.8,2.7,4.1,1,Iris-versicolor 6.2,2.2,4.5,1.5,Iris-versicolor 5.6,2.5,3.9,1.1,Iris-versicolor 5.9,3.2,4.8,1.8,Iris-versicolor 6.1,2.8,4,1.3,Iris-versicolor 6.3,2.5,4.9,1.5,Iris-versicolor 6.1,2.8,4.7,1.2,Iris-versicolor 6.4,2.9,4.3,1.3,Iris-versicolor 6.6,3,4.4,1.4,Iris-versicolor 6.8,2.8,4.8,1.4,Iris-versicolor 0.067,3,5,1.7,Iris-versicolor 0.06,2.9,4.5,1.5,Iris-versicolor 0.057,2.6,3.5,1,Iris-versicolor 0.055,2.4,3.8,1.1,Iris-versicolor 0.055,2.4,3.7,1,Iris-versicolor 5.8,2.7,3.9,1.2,Iris-versicolor 6,2.8,5.1,1.6,Iris-versicolor 5.4,3,4.5,1.5,Iris-versicolor 6,3.4,4.5,1.6,Iris-versicolor 6.7,3.1,4.7,1.5,Iris-versicolor 6.3,2.3,4.4,1.3,Iris-versicolor 5.6,3,4.1,1.3,Iris-versicolor 5.5,2.5,4,1.3,Iris-versicolor 5.5,2.6,4.4,1.2,Iris-versicolor 6.1,3,4.6,1.4,Iris-versicolor 5.8,2.6,4,1.2,Iris-versicolor 5,2.3,3.3,1,Iris-versicolor 5.6,2.7,4.2,1.3,Iris-versicolor 5.7,3,4.2,1.2,versicolor 5.7,2.9,4.2,1.3,versicolor 6.2,2.9,4.3,1.3,versicolor 5.1,2.5,3,1.1,versicolor 5.7,2.8,4.1,1.3,versicolor 6.3,3.3,6,2.5,Iris-virginica 5.8,2.7,5.1,1.9,Iris-virginica 7.1,3,5.9,2.1,Iris-virginica 6.3,2.9,5.6,1.8,Iris-virginica 6.5,3,5.8,2.2,Iris-virginica 7.6,3,6.6,2.1,Iris-virginica 4.9,2.5,4.5,1.7,Iris-virginica 7.3,2.9,6.3,1.8,Iris-virginica 6.7,2.5,5.8,1.8,Iris-virginica 7.2,3.6,6.1,2.5,Iris-virginica 6.5,3.2,5.1,2,Iris-virginica 6.4,2.7,5.3,1.9,Iris-virginica 6.8,3,5.5,2.1,Iris-virginica 5.7,2.5,5,2,Iris-virginica 5.8,2.8,5.1,2.4,Iris-virginica 6.4,3.2,5.3,2.3,Iris-virginica 6.5,3,5.5,1.8,Iris-virginica 7.7,3.8,6.7,2.2,Iris-virginica 7.7,2.6,6.9,2.3,Iris-virginica 6,2.2,5,1.5,Iris-virginica 6.9,3.2,5.7,2.3,Iris-virginica 5.6,2.8,4.9,2,Iris-virginica 5.6,2.8,6.7,2,Iris-virginica 6.3,2.7,4.9,1.8,Iris-virginica 6.7,3.3,5.7,2.1,Iris-virginica 7.2,3.2,6,1.8,Iris-virginica 6.2,2.8,4.8,1.8,Iris-virginica 6.1,3,4.9,1.8,Iris-virginica 6.4,2.8,5.6,2.1,Iris-virginica 7.2,3,5.8,1.6,Iris-virginica 7.4,2.8,6.1,1.9,Iris-virginica 7.9,3.8,6.4,2,Iris-virginica 6.4,2.8,5.6,2.2,Iris-virginica 6.3,2.8,5.1,1.5,Iris-virginica 6.1,2.6,5.6,1.4,Iris-virginica 7.7,3,6.1,2.3,Iris-virginica 6.3,3.4,5.6,2.4,Iris-virginica 6.4,3.1,5.5,1.8,Iris-virginica 6,3,4.8,1.8,Iris-virginica 6.9,3.1,5.4,2.1,Iris-virginica 6.7,3.1,5.6,2.4,Iris-virginica 6.9,3.1,5.1,2.3,Iris-virginica 5.8,2.7,5.1,1.9,Iris-virginica 6.8,3.2,5.9,2.3,Iris-virginica 6.7,3.3,5.7,2.5,Iris-virginica 6.7,3,5.2,2.3,Iris-virginica 6.3,2.5,5,2.3,Iris-virginica 6.5,3,5.2,2,Iris-virginica 6.2,3.4,5.4,2.3,Iris-virginica 5.9,3,5.1,1.8,Iris-virginica -------------------------------------------------------------------------------- /python basics/NUMPY/NUMPY.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": 1, 6 | "metadata": {}, 7 | "outputs": [], 8 | "source": [ 9 | "import numpy as np\n" 10 | ] 11 | }, 12 | { 13 | "cell_type": "code", 14 | "execution_count": 2, 15 | "metadata": {}, 16 | "outputs": [], 17 | "source": [ 18 | "np1 = np.array([1,2,3,4,5])" 19 | ] 20 | }, 21 | { 22 | "cell_type": "code", 23 | "execution_count": 3, 24 | "metadata": {}, 25 | "outputs": [ 26 | { 27 | "data": { 28 | "text/plain": [ 29 | "array([1, 2, 3, 4, 5])" 30 | ] 31 | }, 32 | "execution_count": 3, 33 | "metadata": {}, 34 | "output_type": "execute_result" 35 | } 36 | ], 37 | "source": [ 38 | "np1" 39 | ] 40 | }, 41 | { 42 | "cell_type": "code", 43 | "execution_count": 4, 44 | "metadata": {}, 45 | "outputs": [ 46 | { 47 | "data": { 48 | "text/plain": [ 49 | "numpy.ndarray" 50 | ] 51 | }, 52 | "execution_count": 4, 53 | "metadata": {}, 54 | "output_type": "execute_result" 55 | } 56 | ], 57 | "source": [ 58 | "type(np1)" 59 | ] 60 | }, 61 | { 62 | "cell_type": "code", 63 | "execution_count": 6, 64 | "metadata": {}, 65 | "outputs": [], 66 | "source": [ 67 | "Mat1 = np.array([[1,2],[3,4]])" 68 | ] 69 | }, 70 | { 71 | "cell_type": "code", 72 | "execution_count": 7, 73 | "metadata": {}, 74 | "outputs": [ 75 | { 76 | "data": { 77 | "text/plain": [ 78 | "array([[1, 2],\n", 79 | " [3, 4]])" 80 | ] 81 | }, 82 | "execution_count": 7, 83 | "metadata": {}, 84 | "output_type": "execute_result" 85 | } 86 | ], 87 | "source": [ 88 | "Mat1" 89 | ] 90 | }, 91 | { 92 | "cell_type": "code", 93 | "execution_count": 9, 94 | "metadata": {}, 95 | "outputs": [ 96 | { 97 | "data": { 98 | "text/plain": [ 99 | "(5,)" 100 | ] 101 | }, 102 | "execution_count": 9, 103 | "metadata": {}, 104 | "output_type": "execute_result" 105 | } 106 | ], 107 | "source": [ 108 | "np1.shape\n" 109 | ] 110 | }, 111 | { 112 | "cell_type": "code", 113 | "execution_count": 10, 114 | "metadata": {}, 115 | "outputs": [ 116 | { 117 | "data": { 118 | "text/plain": [ 119 | "(2, 2)" 120 | ] 121 | }, 122 | "execution_count": 10, 123 | "metadata": {}, 124 | "output_type": "execute_result" 125 | } 126 | ], 127 | "source": [ 128 | "Mat1.shape" 129 | ] 130 | }, 131 | { 132 | "cell_type": "code", 133 | "execution_count": 11, 134 | "metadata": {}, 135 | "outputs": [ 136 | { 137 | "data": { 138 | "text/plain": [ 139 | "dtype('int32')" 140 | ] 141 | }, 142 | "execution_count": 11, 143 | "metadata": {}, 144 | "output_type": "execute_result" 145 | } 146 | ], 147 | "source": [ 148 | "Mat1.dtype" 149 | ] 150 | }, 151 | { 152 | "cell_type": "code", 153 | "execution_count": 13, 154 | "metadata": {}, 155 | "outputs": [], 156 | "source": [ 157 | "mat2 = np.arange(0,4,1)" 158 | ] 159 | }, 160 | { 161 | "cell_type": "code", 162 | "execution_count": 14, 163 | "metadata": {}, 164 | "outputs": [ 165 | { 166 | "data": { 167 | "text/plain": [ 168 | "array([0, 1, 2, 3])" 169 | ] 170 | }, 171 | "execution_count": 14, 172 | "metadata": {}, 173 | "output_type": "execute_result" 174 | } 175 | ], 176 | "source": [ 177 | "mat2" 178 | ] 179 | }, 180 | { 181 | "cell_type": "code", 182 | "execution_count": 15, 183 | "metadata": {}, 184 | "outputs": [], 185 | "source": [ 186 | "mat3 = np.linspace(0,10,20)" 187 | ] 188 | }, 189 | { 190 | "cell_type": "code", 191 | "execution_count": 16, 192 | "metadata": {}, 193 | "outputs": [ 194 | { 195 | "data": { 196 | "text/plain": [ 197 | "array([ 0. , 0.52631579, 1.05263158, 1.57894737, 2.10526316,\n", 198 | " 2.63157895, 3.15789474, 3.68421053, 4.21052632, 4.73684211,\n", 199 | " 5.26315789, 5.78947368, 6.31578947, 6.84210526, 7.36842105,\n", 200 | " 7.89473684, 8.42105263, 8.94736842, 9.47368421, 10. ])" 201 | ] 202 | }, 203 | "execution_count": 16, 204 | "metadata": {}, 205 | "output_type": "execute_result" 206 | } 207 | ], 208 | "source": [ 209 | "mat3" 210 | ] 211 | }, 212 | { 213 | "cell_type": "code", 214 | "execution_count": null, 215 | "metadata": {}, 216 | "outputs": [], 217 | "source": [] 218 | }, 219 | { 220 | "cell_type": "code", 221 | "execution_count": null, 222 | "metadata": {}, 223 | "outputs": [], 224 | "source": [] 225 | }, 226 | { 227 | "cell_type": "code", 228 | "execution_count": null, 229 | "metadata": {}, 230 | "outputs": [], 231 | "source": [] 232 | } 233 | ], 234 | "metadata": { 235 | "kernelspec": { 236 | "display_name": "Python 3", 237 | "language": "python", 238 | "name": "python3" 239 | }, 240 | "language_info": { 241 | "codemirror_mode": { 242 | "name": "ipython", 243 | "version": 3 244 | }, 245 | "file_extension": ".py", 246 | "mimetype": "text/x-python", 247 | "name": "python", 248 | "nbconvert_exporter": "python", 249 | "pygments_lexer": "ipython3", 250 | "version": "3.7.4" 251 | } 252 | }, 253 | "nbformat": 4, 254 | "nbformat_minor": 2 255 | } 256 | -------------------------------------------------------------------------------- /LSTM/Untitled1.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": 1, 6 | "metadata": {}, 7 | "outputs": [], 8 | "source": [ 9 | "import numpy as np\n", 10 | "import matplotlib.pyplot as plt \n", 11 | "import pandas as pd\n" 12 | ] 13 | }, 14 | { 15 | "cell_type": "code", 16 | "execution_count": 10, 17 | "metadata": {}, 18 | "outputs": [], 19 | "source": [ 20 | "\n", 21 | "dataset_train = pd.read_csv('NSE-TATAGLOBAL.csv')\n", 22 | "training_set=dataset_train.iloc[:,1:2].values" 23 | ] 24 | }, 25 | { 26 | "cell_type": "code", 27 | "execution_count": 11, 28 | "metadata": {}, 29 | "outputs": [ 30 | { 31 | "data": { 32 | "text/html": [ 33 | "
\n", 34 | "\n", 47 | "\n", 48 | " \n", 49 | " \n", 50 | " \n", 51 | " \n", 52 | " \n", 53 | " \n", 54 | " \n", 55 | " \n", 56 | " \n", 57 | " \n", 58 | " \n", 59 | " \n", 60 | " \n", 61 | " \n", 62 | " \n", 63 | " \n", 64 | " \n", 65 | " \n", 66 | " \n", 67 | " \n", 68 | " \n", 69 | " \n", 70 | " \n", 71 | " \n", 72 | " \n", 73 | " \n", 74 | " \n", 75 | " \n", 76 | " \n", 77 | " \n", 78 | " \n", 79 | " \n", 80 | " \n", 81 | " \n", 82 | " \n", 83 | " \n", 84 | " \n", 85 | " \n", 86 | " \n", 87 | " \n", 88 | " \n", 89 | " \n", 90 | " \n", 91 | " \n", 92 | " \n", 93 | " \n", 94 | " \n", 95 | " \n", 96 | " \n", 97 | " \n", 98 | " \n", 99 | " \n", 100 | " \n", 101 | " \n", 102 | " \n", 103 | " \n", 104 | " \n", 105 | " \n", 106 | " \n", 107 | " \n", 108 | " \n", 109 | " \n", 110 | " \n", 111 | " \n", 112 | " \n", 113 | " \n", 114 | " \n", 115 | " \n", 116 | " \n", 117 | " \n", 118 | "
DateOpenHighLowLastCloseTotal Trade QuantityTurnover (Lacs)
02018-09-28234.05235.95230.20233.50233.7530699147162.35
12018-09-27234.55236.80231.10233.80233.25508285911859.95
22018-09-26240.00240.00232.50235.00234.2522409095248.60
32018-09-25233.30236.75232.00236.25236.1023493685503.90
42018-09-24233.55239.20230.75234.00233.3034235097999.55
\n", 119 | "
" 120 | ], 121 | "text/plain": [ 122 | " Date Open High Low Last Close Total Trade Quantity \\\n", 123 | "0 2018-09-28 234.05 235.95 230.20 233.50 233.75 3069914 \n", 124 | "1 2018-09-27 234.55 236.80 231.10 233.80 233.25 5082859 \n", 125 | "2 2018-09-26 240.00 240.00 232.50 235.00 234.25 2240909 \n", 126 | "3 2018-09-25 233.30 236.75 232.00 236.25 236.10 2349368 \n", 127 | "4 2018-09-24 233.55 239.20 230.75 234.00 233.30 3423509 \n", 128 | "\n", 129 | " Turnover (Lacs) \n", 130 | "0 7162.35 \n", 131 | "1 11859.95 \n", 132 | "2 5248.60 \n", 133 | "3 5503.90 \n", 134 | "4 7999.55 " 135 | ] 136 | }, 137 | "execution_count": 11, 138 | "metadata": {}, 139 | "output_type": "execute_result" 140 | } 141 | ], 142 | "source": [ 143 | "dataset_train.head()" 144 | ] 145 | }, 146 | { 147 | "cell_type": "code", 148 | "execution_count": 12, 149 | "metadata": {}, 150 | "outputs": [], 151 | "source": [ 152 | "from sklearn.preprocessing import MinMaxScaler\n", 153 | "sc = MinMaxScaler(feature_range=(0,1))\n", 154 | "training_set_scaled = sc.fit_transform(training_set)" 155 | ] 156 | }, 157 | { 158 | "cell_type": "code", 159 | "execution_count": 14, 160 | "metadata": {}, 161 | "outputs": [ 162 | { 163 | "ename": "AttributeError", 164 | "evalue": "'numpy.ndarray' object has no attribute 'append'", 165 | "output_type": "error", 166 | "traceback": [ 167 | "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", 168 | "\u001b[1;31mAttributeError\u001b[0m Traceback (most recent call last)", 169 | "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[0;32m 2\u001b[0m \u001b[0my_train\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m[\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m60\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m2035\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 4\u001b[1;33m \u001b[0mX_train\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtraining_set_scaled\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m-\u001b[0m\u001b[1;36m60\u001b[0m\u001b[1;33m:\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 5\u001b[0m \u001b[0my_train\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtraining_set_scaled\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 6\u001b[0m \u001b[0mX_train\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0my_train\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0marray\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX_train\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0marray\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0my_train\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", 170 | "\u001b[1;31mAttributeError\u001b[0m: 'numpy.ndarray' object has no attribute 'append'" 171 | ] 172 | } 173 | ], 174 | "source": [ 175 | "X_train = []\n", 176 | "y_train = []\n", 177 | "for i in range(60, 2035):\n", 178 | " X_train.append(training_set_scaled[i-60:i,0])\n", 179 | " y_train.append(training_set_scaled[i,0])\n", 180 | " X_train,y_train = np.array(X_train),np.array(y_train) \n", 181 | " X_train = np.reshape(X_train,(X_train.shape[0], X_train.shape[1],1))" 182 | ] 183 | }, 184 | { 185 | "cell_type": "code", 186 | "execution_count": null, 187 | "metadata": {}, 188 | "outputs": [], 189 | "source": [] 190 | } 191 | ], 192 | "metadata": { 193 | "kernelspec": { 194 | "display_name": "Python 3", 195 | "language": "python", 196 | "name": "python3" 197 | }, 198 | "language_info": { 199 | "codemirror_mode": { 200 | "name": "ipython", 201 | "version": 3 202 | }, 203 | "file_extension": ".py", 204 | "mimetype": "text/x-python", 205 | "name": "python", 206 | "nbconvert_exporter": "python", 207 | "pygments_lexer": "ipython3", 208 | "version": "3.7.4" 209 | } 210 | }, 211 | "nbformat": 4, 212 | "nbformat_minor": 2 213 | } 214 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /K-means-cluster/K-MEANS.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": 2, 6 | "metadata": {}, 7 | "outputs": [], 8 | "source": [ 9 | "import pandas as pd\n", 10 | "import numpy as np\n", 11 | "import matplotlib.pyplot as plt\n", 12 | "%matplotlib inline" 13 | ] 14 | }, 15 | { 16 | "cell_type": "code", 17 | "execution_count": 3, 18 | "metadata": {}, 19 | "outputs": [], 20 | "source": [ 21 | "df = pd.DataFrame({\n", 22 | " 'x': [12,20,28,18,29,33,24,45,45,52,51,52,55,53,55,61,64,69,72],\n", 23 | " 'y':[39,36,30,52,54,46,55,59,63,70,66,63,58,23,14,8,19,7,24]\n", 24 | " })\n" 25 | ] 26 | }, 27 | { 28 | "cell_type": "code", 29 | "execution_count": 4, 30 | "metadata": {}, 31 | "outputs": [ 32 | { 33 | "data": { 34 | "text/plain": [ 35 | "
" 36 | ] 37 | }, 38 | "metadata": {}, 39 | "output_type": "display_data" 40 | } 41 | ], 42 | "source": [ 43 | "np.random.seed(200)\n", 44 | "k=3\n", 45 | "centroids = {\n", 46 | " i+1:[np.random.randint(0,80),np.random.randint(0,9)]\n", 47 | " for i in range(k)\n", 48 | " \n", 49 | "}\n", 50 | "fig = plt.figure(figsize=(5,5))\n" 51 | ] 52 | }, 53 | { 54 | "cell_type": "code", 55 | "execution_count": 6, 56 | "metadata": {}, 57 | "outputs": [ 58 | { 59 | "data": { 60 | "image/png": "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\n", 61 | "text/plain": [ 62 | "
" 63 | ] 64 | }, 65 | "metadata": { 66 | "needs_background": "light" 67 | }, 68 | "output_type": "display_data" 69 | } 70 | ], 71 | "source": [ 72 | "plt.scatter(df['x'],df['y'],color='k')\n", 73 | "colmap = {1: 'r',2:'g',3: 'b'}\n", 74 | "for i in centroids.keys():\n", 75 | " plt.scatter(*centroids[i], color=colmap[i])\n", 76 | "plt.xlim(0,80)\n", 77 | "plt.ylim(0,80)\n", 78 | "plt.show()\n" 79 | ] 80 | }, 81 | { 82 | "cell_type": "code", 83 | "execution_count": 12, 84 | "metadata": {}, 85 | "outputs": [ 86 | { 87 | "name": "stdout", 88 | "output_type": "stream", 89 | "text": [ 90 | " x y distance_from_1 distance_from_2 distance_from_3 closest color\n", 91 | "0 12 39 41.436699 64.498062 72.006944 1 r\n", 92 | "1 20 36 36.496575 56.080300 63.529521 1 r\n", 93 | "2 28 30 30.066593 46.141088 53.665631 1 r\n", 94 | "3 18 52 52.611786 67.268120 74.027022 1 r\n", 95 | "4 29 54 54.083269 61.073726 67.178866 1 r\n" 96 | ] 97 | }, 98 | { 99 | "data": { 100 | "image/png": "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\n", 101 | "text/plain": [ 102 | "
" 103 | ] 104 | }, 105 | "metadata": { 106 | "needs_background": "light" 107 | }, 108 | "output_type": "display_data" 109 | } 110 | ], 111 | "source": [ 112 | "def assignment(df, centroids):\n", 113 | " for i in centroids.keys():\n", 114 | " # sqrt((x1 - x2)^2 - (y1 - y2)^2)\n", 115 | " df['distance_from_{}'.format(i)] = (\n", 116 | " np.sqrt(\n", 117 | " (df['x'] - centroids[i][0]) ** 2\n", 118 | " + (df['y'] - centroids[i][1]) ** 2\n", 119 | " )\n", 120 | " )\n", 121 | " centroid_distance_cols = ['distance_from_{}'.format(i) for i in centroids.keys()]\n", 122 | " df['closest'] = df.loc[:, centroid_distance_cols].idxmin(axis=1)\n", 123 | " df['closest'] = df['closest'].map(lambda x: int(x.lstrip('distance_from_')))\n", 124 | " df['color'] = df['closest'].map(lambda x: colmap[x])\n", 125 | " return df\n", 126 | "\n", 127 | "df = assignment(df, centroids)\n", 128 | "print(df.head())\n", 129 | "\n", 130 | "fig = plt.figure(figsize=(5, 5))\n", 131 | "plt.scatter(df['x'], df['y'], color=df['color'], alpha=0.5, edgecolor='k')\n", 132 | "for i in centroids.keys():\n", 133 | " plt.scatter(*centroids[i], color=colmap[i])\n", 134 | "plt.xlim(0, 80)\n", 135 | "plt.ylim(0, 80)\n", 136 | "plt.show()" 137 | ] 138 | }, 139 | { 140 | "cell_type": "code", 141 | "execution_count": null, 142 | "metadata": {}, 143 | "outputs": [], 144 | "source": [] 145 | } 146 | ], 147 | "metadata": { 148 | "kernelspec": { 149 | "display_name": "Python 3", 150 | "language": "python", 151 | "name": "python3" 152 | }, 153 | "language_info": { 154 | "codemirror_mode": { 155 | "name": "ipython", 156 | "version": 3 157 | }, 158 | "file_extension": ".py", 159 | "mimetype": "text/x-python", 160 | "name": "python", 161 | "nbconvert_exporter": "python", 162 | "pygments_lexer": "ipython3", 163 | "version": "3.7.4" 164 | } 165 | }, 166 | "nbformat": 4, 167 | "nbformat_minor": 2 168 | } 169 | -------------------------------------------------------------------------------- /Autoencoder/Autoencoder.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "## AUTOENCODERS\n", 8 | "In this notebook you will find an explanation of what is an autoencoder, how it works, and see an implementation of an autoencoder in TensorFlow. By the end of this notebook, you should be able to create simple autoencoders and how to apply them to problems that involves unsupervised learning." 9 | ] 10 | }, 11 | { 12 | "cell_type": "markdown", 13 | "metadata": { 14 | "colab_type": "text", 15 | "id": "view-in-github" 16 | }, 17 | "source": [ 18 | "\"Open" 19 | ] 20 | }, 21 | { 22 | "cell_type": "markdown", 23 | "metadata": {}, 24 | "source": [ 25 | "\n", 26 | "## Introduction\n", 27 | "An autoencoder, also known as autoassociator or Diabolo networks, is an artificial neural network employed to recreate the given input. It takes a set of unlabeled inputs, encodes them and then tries to extract the most valuable information from them. They are used for feature extraction, learning generative models of data, dimensionality reduction and can be used for compression.\n", 28 | "\n", 29 | "A 2006 paper named Reducing the Dimensionality of Data with Neural Networks, done by G. E. Hinton and R. R. Salakhutdinov, showed better results than years of refining other types of network, and was a breakthrough in the field of Neural Networks, a field that was \"stagnant\" for 10 years.\n", 30 | "\n", 31 | "Now, autoencoders, based on Restricted Boltzmann Machines, are employed in some of the largest deep learning applications. They are the building blocks of Deep Belief Networks (DBN)." 32 | ] 33 | }, 34 | { 35 | "cell_type": "markdown", 36 | "metadata": {}, 37 | "source": [ 38 | "\n", 39 | "## Autoencoder Structure\n", 40 | "\n", 41 | "\n", 42 | "An autoencoder can be divided in two parts, the encoder and the decoder.\n", 43 | "\n", 44 | "The encoder needs to compress the representation of an input. In this case we are going to reduce the dimension the face of our actor, from 2000 dimensions to only 30 dimensions, by running the data through layers of our encoder.\n", 45 | "\n", 46 | "The decoder works like encoder network in reverse. It works to recreate the input, as closely as possible. This plays an important role during training, because it forces the autoencoder to select the most important features in the compressed representation" 47 | ] 48 | }, 49 | { 50 | "cell_type": "code", 51 | "execution_count": 0, 52 | "metadata": { 53 | "colab": {}, 54 | "colab_type": "code", 55 | "id": "RsuGfD8--DUG" 56 | }, 57 | "outputs": [], 58 | "source": [ 59 | "import numpy as np\n", 60 | "import tensorflow as tf\n", 61 | "from tensorflow import keras\n", 62 | "from matplotlib import pyplot as plt" 63 | ] 64 | }, 65 | { 66 | "cell_type": "code", 67 | "execution_count": 0, 68 | "metadata": { 69 | "colab": { 70 | "base_uri": "https://localhost:8080/", 71 | "height": 35 72 | }, 73 | "colab_type": "code", 74 | "id": "Lrt5tiRJ-DSt", 75 | "outputId": "d7a7039b-a8c6-492c-cad2-bdf0a73494de" 76 | }, 77 | "outputs": [ 78 | { 79 | "name": "stderr", 80 | "output_type": "stream", 81 | "text": [ 82 | "Using TensorFlow backend.\n" 83 | ] 84 | } 85 | ], 86 | "source": [ 87 | "from keras.datasets import mnist\n", 88 | "from keras.layers import Input, Dense\n", 89 | "from keras.models import Model" 90 | ] 91 | }, 92 | { 93 | "cell_type": "code", 94 | "execution_count": 0, 95 | "metadata": { 96 | "colab": { 97 | "base_uri": "https://localhost:8080/", 98 | "height": 54 99 | }, 100 | "colab_type": "code", 101 | "id": "a5I-BA7K-DON", 102 | "outputId": "ddd43dc1-bac7-47e7-e7a6-cf95085ecece" 103 | }, 104 | "outputs": [ 105 | { 106 | "name": "stdout", 107 | "output_type": "stream", 108 | "text": [ 109 | "Downloading data from https://s3.amazonaws.com/img-datasets/mnist.npz\n", 110 | "11493376/11490434 [==============================] - 2s 0us/step\n" 111 | ] 112 | } 113 | ], 114 | "source": [ 115 | "(x_train, y_train), (x_test, y_test) = mnist.load_data()" 116 | ] 117 | }, 118 | { 119 | "cell_type": "code", 120 | "execution_count": 0, 121 | "metadata": { 122 | "colab": { 123 | "base_uri": "https://localhost:8080/", 124 | "height": 35 125 | }, 126 | "colab_type": "code", 127 | "id": "jFiRn0ef_hHJ", 128 | "outputId": "cf3ad53b-98c9-4b7f-95ef-bd098775a2c6" 129 | }, 130 | "outputs": [ 131 | { 132 | "data": { 133 | "text/plain": [ 134 | "(60000, 28, 28)" 135 | ] 136 | }, 137 | "execution_count": 5, 138 | "metadata": { 139 | "tags": [] 140 | }, 141 | "output_type": "execute_result" 142 | } 143 | ], 144 | "source": [ 145 | "x_train.shape" 146 | ] 147 | }, 148 | { 149 | "cell_type": "code", 150 | "execution_count": 0, 151 | "metadata": { 152 | "colab": {}, 153 | "colab_type": "code", 154 | "id": "zvjFj5PL_rVH" 155 | }, 156 | "outputs": [], 157 | "source": [ 158 | "x_train = x_train.astype('float32')/255.0\n", 159 | "x_test = x_test.astype('float32')/255.0" 160 | ] 161 | }, 162 | { 163 | "cell_type": "markdown", 164 | "metadata": { 165 | "colab_type": "text", 166 | "id": "1KS4RuDZ6Kuz" 167 | }, 168 | "source": [ 169 | "Reshaping images, Flattening them to feed to a Dense network\n", 170 | "\n", 171 | "we won't do this in ConvNets" 172 | ] 173 | }, 174 | { 175 | "cell_type": "code", 176 | "execution_count": 0, 177 | "metadata": { 178 | "colab": {}, 179 | "colab_type": "code", 180 | "id": "lv-AALS9AA7r" 181 | }, 182 | "outputs": [], 183 | "source": [ 184 | "x_train = x_train.reshape(len(x_train), (x_train.shape[1]*x_train.shape[2]))\n", 185 | "x_test = x_test.reshape(len(x_test), (x_test.shape[1]*x_test.shape[2]))" 186 | ] 187 | }, 188 | { 189 | "cell_type": "code", 190 | "execution_count": 0, 191 | "metadata": { 192 | "colab": {}, 193 | "colab_type": "code", 194 | "id": "Z09aungJAG6E" 195 | }, 196 | "outputs": [], 197 | "source": [ 198 | "encoding_dim = 32\n", 199 | "\n", 200 | "input_img = Input(shape = (784, ))\n", 201 | "encoded = Dense(128, activation='relu')(input_img)\n", 202 | "encoded = Dense(encoding_dim, activation='relu')(encoded)\n", 203 | "\n", 204 | "\n", 205 | "decoded = Dense(128, activation='relu')(encoded)\n", 206 | "decoded = Dense(784, activation='sigmoid')(decoded)\n", 207 | "\n", 208 | "autoencoder = Model(input_img, decoded)" 209 | ] 210 | }, 211 | { 212 | "cell_type": "code", 213 | "execution_count": 0, 214 | "metadata": { 215 | "colab": {}, 216 | "colab_type": "code", 217 | "id": "HN8ANrYPEvfl" 218 | }, 219 | "outputs": [], 220 | "source": [ 221 | "encoder = Model(input_img, encoded)\n", 222 | "encoded_input = Input(shape=(encoding_dim, ))\n", 223 | "decode_layer1 = autoencoder.layers[-2]\n", 224 | "decode_layer2 = autoencoder.layers[-1]\n", 225 | "decoder = Model(encoded_input, decode_layer2(decode_layer1(encoded_input)))" 226 | ] 227 | }, 228 | { 229 | "cell_type": "code", 230 | "execution_count": 0, 231 | "metadata": { 232 | "colab": { 233 | "base_uri": "https://localhost:8080/", 234 | "height": 35 235 | }, 236 | "colab_type": "code", 237 | "id": "skKxFoz_4rCS", 238 | "outputId": "24f6e177-3127-4169-fd00-df67d3ebe3ef" 239 | }, 240 | "outputs": [ 241 | { 242 | "data": { 243 | "text/plain": [ 244 | "" 245 | ] 246 | }, 247 | "execution_count": 35, 248 | "metadata": { 249 | "tags": [] 250 | }, 251 | "output_type": "execute_result" 252 | } 253 | ], 254 | "source": [ 255 | "autoencoder.get_layer('dense_5')" 256 | ] 257 | }, 258 | { 259 | "cell_type": "code", 260 | "execution_count": 0, 261 | "metadata": { 262 | "colab": {}, 263 | "colab_type": "code", 264 | "id": "6tVqkhvHAIPz" 265 | }, 266 | "outputs": [], 267 | "source": [ 268 | "autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy', metrics=['accuracy'])" 269 | ] 270 | }, 271 | { 272 | "cell_type": "code", 273 | "execution_count": 0, 274 | "metadata": { 275 | "colab": { 276 | "base_uri": "https://localhost:8080/", 277 | "height": 348 278 | }, 279 | "colab_type": "code", 280 | "id": "PUBcoIWKzdVL", 281 | "outputId": "4a1f574e-0b02-49db-c228-c4269ee9017e" 282 | }, 283 | "outputs": [ 284 | { 285 | "name": "stdout", 286 | "output_type": "stream", 287 | "text": [ 288 | "Model: \"model_6\"\n", 289 | "_________________________________________________________________\n", 290 | "Layer (type) Output Shape Param # \n", 291 | "=================================================================\n", 292 | "input_6 (InputLayer) (None, 784) 0 \n", 293 | "_________________________________________________________________\n", 294 | "dense_3 (Dense) (None, 128) 100480 \n", 295 | "_________________________________________________________________\n", 296 | "dense_4 (Dense) (None, 32) 4128 \n", 297 | "_________________________________________________________________\n", 298 | "dense_5 (Dense) (None, 128) 4224 \n", 299 | "_________________________________________________________________\n", 300 | "dense_6 (Dense) (None, 784) 101136 \n", 301 | "=================================================================\n", 302 | "Total params: 209,968\n", 303 | "Trainable params: 209,968\n", 304 | "Non-trainable params: 0\n", 305 | "_________________________________________________________________\n" 306 | ] 307 | } 308 | ], 309 | "source": [ 310 | "autoencoder.summary()" 311 | ] 312 | }, 313 | { 314 | "cell_type": "code", 315 | "execution_count": 0, 316 | "metadata": { 317 | "colab": { 318 | "base_uri": "https://localhost:8080/", 319 | "height": 403 320 | }, 321 | "colab_type": "code", 322 | "id": "HLMkoI-JCgPX", 323 | "outputId": "e2053547-3301-4923-81b2-bfe051688c25" 324 | }, 325 | "outputs": [ 326 | { 327 | "name": "stdout", 328 | "output_type": "stream", 329 | "text": [ 330 | "Train on 60000 samples, validate on 10000 samples\n", 331 | "Epoch 1/10\n", 332 | "60000/60000 [==============================] - 12s 202us/step - loss: 0.2129 - acc: 0.7929 - val_loss: 0.1578 - val_acc: 0.8043\n", 333 | "Epoch 2/10\n", 334 | "60000/60000 [==============================] - 12s 196us/step - loss: 0.1422 - acc: 0.8077 - val_loss: 0.1278 - val_acc: 0.8080\n", 335 | "Epoch 3/10\n", 336 | "60000/60000 [==============================] - 12s 195us/step - loss: 0.1226 - acc: 0.8108 - val_loss: 0.1157 - val_acc: 0.8114\n", 337 | "Epoch 4/10\n", 338 | "60000/60000 [==============================] - 12s 195us/step - loss: 0.1142 - acc: 0.8118 - val_loss: 0.1086 - val_acc: 0.8115\n", 339 | "Epoch 5/10\n", 340 | "60000/60000 [==============================] - 12s 198us/step - loss: 0.1088 - acc: 0.8125 - val_loss: 0.1063 - val_acc: 0.8110\n", 341 | "Epoch 6/10\n", 342 | "60000/60000 [==============================] - 12s 196us/step - loss: 0.1050 - acc: 0.8129 - val_loss: 0.1020 - val_acc: 0.8117\n", 343 | "Epoch 7/10\n", 344 | "60000/60000 [==============================] - 12s 195us/step - loss: 0.1019 - acc: 0.8132 - val_loss: 0.0985 - val_acc: 0.8126\n", 345 | "Epoch 8/10\n", 346 | "60000/60000 [==============================] - 12s 196us/step - loss: 0.0994 - acc: 0.8135 - val_loss: 0.0968 - val_acc: 0.8127\n", 347 | "Epoch 9/10\n", 348 | "60000/60000 [==============================] - 12s 196us/step - loss: 0.0975 - acc: 0.8137 - val_loss: 0.0952 - val_acc: 0.8130\n", 349 | "Epoch 10/10\n", 350 | "60000/60000 [==============================] - 12s 192us/step - loss: 0.0961 - acc: 0.8138 - val_loss: 0.0936 - val_acc: 0.8131\n" 351 | ] 352 | } 353 | ], 354 | "source": [ 355 | "hist = autoencoder.fit(x_train, x_train, epochs=10, validation_data=(x_test, x_test))" 356 | ] 357 | }, 358 | { 359 | "cell_type": "code", 360 | "execution_count": 0, 361 | "metadata": { 362 | "colab": { 363 | "base_uri": "https://localhost:8080/", 364 | "height": 287 365 | }, 366 | "colab_type": "code", 367 | "id": "n4xxDcKfEV8_", 368 | "outputId": "77bcd685-2bd1-4eb2-9eee-e7e2c08cf303" 369 | }, 370 | "outputs": [ 371 | { 372 | "data": { 373 | "text/plain": [ 374 | "" 375 | ] 376 | }, 377 | "execution_count": 38, 378 | "metadata": { 379 | "tags": [] 380 | }, 381 | "output_type": "execute_result" 382 | }, 383 | { 384 | "data": { 385 | "image/png": "iVBORw0KGgoAAAANSUhEUgAAAP8AAAD8CAYAAAC4nHJkAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\ngg==\n", 386 | "text/plain": [ 387 | "
" 388 | ] 389 | }, 390 | "metadata": { 391 | "tags": [] 392 | }, 393 | "output_type": "display_data" 394 | } 395 | ], 396 | "source": [ 397 | "encoded_images = encoder.predict(x_test)\n", 398 | "encoded_images.shape\n", 399 | "predicted = decoder.predict(encoded_images)\n", 400 | "plt.imshow(predicted[0].reshape(28, 28))" 401 | ] 402 | }, 403 | { 404 | "cell_type": "code", 405 | "execution_count": 0, 406 | "metadata": { 407 | "colab": { 408 | "base_uri": "https://localhost:8080/", 409 | "height": 269 410 | }, 411 | "colab_type": "code", 412 | "id": "3H3Ekx1SHp5y", 413 | "outputId": "e2c12384-3645-45fa-a46e-6aecdb259a2d" 414 | }, 415 | "outputs": [ 416 | { 417 | "data": { 418 | "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXQAAAD8CAYAAABn919SAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nkAgSOgAkgoQOAIn4f39N1HbojQUaAAAAAElFTkSuQmCC\n", 419 | "text/plain": [ 420 | "
" 421 | ] 422 | }, 423 | "metadata": { 424 | "tags": [] 425 | }, 426 | "output_type": "display_data" 427 | } 428 | ], 429 | "source": [ 430 | "def plot_imgs(index=0):\n", 431 | " f = plt.figure()\n", 432 | " f.add_subplot(1,3, 1)\n", 433 | " plt.imshow(x_test[index].reshape(28, 28))\n", 434 | " f.add_subplot(1,3, 2)\n", 435 | " plt.imshow(encoded_images[index].reshape(-1, 1))\n", 436 | " f.add_subplot(1,3, 3)\n", 437 | " plt.imshow(predicted[index].reshape(28, 28))\n", 438 | " plt.show(block=True)\n", 439 | " \n", 440 | "plot_imgs(2)" 441 | ] 442 | }, 443 | { 444 | "cell_type": "markdown", 445 | "metadata": { 446 | "colab_type": "text", 447 | "id": "8lkIoRva6ewM" 448 | }, 449 | "source": [ 450 | "# Let's use Convolutional Neural Nets to get better results" 451 | ] 452 | }, 453 | { 454 | "cell_type": "code", 455 | "execution_count": 0, 456 | "metadata": { 457 | "colab": {}, 458 | "colab_type": "code", 459 | "id": "4UorTYac692G" 460 | }, 461 | "outputs": [], 462 | "source": [ 463 | "from keras.layers import Dense, Input, UpSampling2D, Conv2D" 464 | ] 465 | }, 466 | { 467 | "cell_type": "markdown", 468 | "metadata": { 469 | "colab_type": "text", 470 | "id": "u8p2wwLa6qbB" 471 | }, 472 | "source": [ 473 | "Getting data" 474 | ] 475 | }, 476 | { 477 | "cell_type": "code", 478 | "execution_count": 0, 479 | "metadata": { 480 | "colab": {}, 481 | "colab_type": "code", 482 | "id": "07Ixl4YT6eQZ" 483 | }, 484 | "outputs": [], 485 | "source": [ 486 | "(x_train, y_train), (x_test, y_test) = mnist.load_data()" 487 | ] 488 | }, 489 | { 490 | "cell_type": "code", 491 | "execution_count": 0, 492 | "metadata": { 493 | "colab": {}, 494 | "colab_type": "code", 495 | "id": "-tmJMUnx6eVQ" 496 | }, 497 | "outputs": [], 498 | "source": [ 499 | "x_train = x_train.astype('float32')/255.0\n", 500 | "x_test = x_test.astype('float32')/255.0" 501 | ] 502 | }, 503 | { 504 | "cell_type": "code", 505 | "execution_count": 0, 506 | "metadata": { 507 | "colab": {}, 508 | "colab_type": "code", 509 | "id": "ZLPajgLH8ai4" 510 | }, 511 | "outputs": [], 512 | "source": [ 513 | "x_train = x_train.reshape((60000, 28, 28, 1))\n", 514 | "x_test = x_test.reshape((10000, 28, 28, 1))" 515 | ] 516 | }, 517 | { 518 | "cell_type": "code", 519 | "execution_count": 0, 520 | "metadata": { 521 | "colab": {}, 522 | "colab_type": "code", 523 | "id": "d2PouxDW7eB0" 524 | }, 525 | "outputs": [], 526 | "source": [ 527 | "img_height, img_width, _ = x_train[1].shape" 528 | ] 529 | }, 530 | { 531 | "cell_type": "code", 532 | "execution_count": 0, 533 | "metadata": { 534 | "colab": {}, 535 | "colab_type": "code", 536 | "id": "CHctX-5G6wTb" 537 | }, 538 | "outputs": [], 539 | "source": [ 540 | "def CNN_AE():\n", 541 | " input_img = Input(shape=(img_width, img_height, 1))\n", 542 | " \n", 543 | " # Encoding network\n", 544 | " x = Conv2D(16, (3, 3), activation='relu', padding='same', strides=2)(input_img)\n", 545 | " x = Conv2D(32, (3, 3), activation='relu', padding='same', strides=2)(x)\n", 546 | " encoded = Conv2D(32, (2, 2), activation='relu', padding=\"same\", strides=2)(x)\n", 547 | "\n", 548 | " # Decoding network\n", 549 | " x = Conv2D(32, (2, 2), activation='relu', padding=\"same\")(encoded)\n", 550 | " x = UpSampling2D((2, 2))(x)\n", 551 | " x = Conv2D(32, (3, 3), activation='relu', padding='same')(x)\n", 552 | " x = UpSampling2D((2, 2))(x)\n", 553 | " x = Conv2D(16, (3, 3), activation='relu')(x)\n", 554 | " x = UpSampling2D((2, 2))(x)\n", 555 | " decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(x)\n", 556 | " \n", 557 | " encoder = Model(input_img, encoded)\n", 558 | " \n", 559 | " return Model(input_img, decoded), encoder" 560 | ] 561 | }, 562 | { 563 | "cell_type": "code", 564 | "execution_count": 0, 565 | "metadata": { 566 | "colab": {}, 567 | "colab_type": "code", 568 | "id": "euWIUw7i9W39" 569 | }, 570 | "outputs": [], 571 | "source": [] 572 | }, 573 | { 574 | "cell_type": "code", 575 | "execution_count": 0, 576 | "metadata": { 577 | "colab": {}, 578 | "colab_type": "code", 579 | "id": "a-0v2iI16wVm" 580 | }, 581 | "outputs": [], 582 | "source": [ 583 | "model_cnn, encoder = CNN_AE()\n", 584 | "model_cnn.compile(optimizer='adadelta', loss='binary_crossentropy')" 585 | ] 586 | }, 587 | { 588 | "cell_type": "code", 589 | "execution_count": 0, 590 | "metadata": { 591 | "colab": { 592 | "base_uri": "https://localhost:8080/", 593 | "height": 72 594 | }, 595 | "colab_type": "code", 596 | "id": "9RikWIEy6wa4", 597 | "outputId": "ee777875-aea8-4e50-a9fe-7b1b436008f8" 598 | }, 599 | "outputs": [ 600 | { 601 | "name": "stdout", 602 | "output_type": "stream", 603 | "text": [ 604 | "Train on 60000 samples, validate on 10000 samples\n", 605 | "Epoch 1/1\n", 606 | "60000/60000 [==============================] - 20s 339us/step - loss: 0.0899 - val_loss: 0.0844\n" 607 | ] 608 | } 609 | ], 610 | "source": [ 611 | "cnn_hist = model_cnn.fit(x_train, x_train, validation_data=(x_test, x_test))" 612 | ] 613 | }, 614 | { 615 | "cell_type": "code", 616 | "execution_count": 0, 617 | "metadata": { 618 | "colab": {}, 619 | "colab_type": "code", 620 | "id": "uOJoBgDd6weQ" 621 | }, 622 | "outputs": [], 623 | "source": [ 624 | "reconstruct = model_cnn.predict(x_test)" 625 | ] 626 | }, 627 | { 628 | "cell_type": "code", 629 | "execution_count": 0, 630 | "metadata": { 631 | "colab": { 632 | "base_uri": "https://localhost:8080/", 633 | "height": 131 634 | }, 635 | "colab_type": "code", 636 | "id": "G15_xNl8_Wyz", 637 | "outputId": "136c1df9-e1bf-442f-f020-5393579af9b0" 638 | }, 639 | "outputs": [ 640 | { 641 | "data": { 642 | "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlMAAAByCAYAAAB3LlRSAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nRERERC6wM0VERETkwv8DEqNmGw3hwBEAAAAASUVORK5CYII=\n", 643 | "text/plain": [ 644 | "
" 645 | ] 646 | }, 647 | "metadata": { 648 | "tags": [] 649 | }, 650 | "output_type": "display_data" 651 | } 652 | ], 653 | "source": [ 654 | "def plot_imgs_for_cnn(index=0):\n", 655 | " f = plt.figure(figsize=(10, 10))\n", 656 | " f.add_subplot(1,6, 1)\n", 657 | " plt.imshow(x_test[index].reshape(28, 28))\n", 658 | " \n", 659 | " \n", 660 | " f.add_subplot(1,6, 2)\n", 661 | " plt.imshow(encoded_images[index][:, :, 0])\n", 662 | " f.add_subplot(1,6, 3)\n", 663 | " plt.imshow(encoded_images[index][:, :, 1])\n", 664 | " f.add_subplot(1,6, 4)\n", 665 | " plt.imshow(encoded_images[index][:, :, 2])\n", 666 | " f.add_subplot(1,6, 5)\n", 667 | " plt.imshow(encoded_images[index][:, :, 3])\n", 668 | " \n", 669 | " \n", 670 | " f.add_subplot(1,6, 6)\n", 671 | " plt.imshow(reconstruct[index].reshape(28,28))\n", 672 | " \n", 673 | " plt.show(block=True)\n", 674 | " \n", 675 | "plot_imgs_for_cnn(3)" 676 | ] 677 | }, 678 | { 679 | "cell_type": "code", 680 | "execution_count": 0, 681 | "metadata": { 682 | "colab": {}, 683 | "colab_type": "code", 684 | "id": "_p4rclEL_0A5" 685 | }, 686 | "outputs": [], 687 | "source": [] 688 | }, 689 | { 690 | "cell_type": "code", 691 | "execution_count": 0, 692 | "metadata": { 693 | "colab": {}, 694 | "colab_type": "code", 695 | "id": "g1alULdqIIyb" 696 | }, 697 | "outputs": [], 698 | "source": [] 699 | }, 700 | { 701 | "cell_type": "markdown", 702 | "metadata": { 703 | "colab_type": "text", 704 | "id": "RCivQ5wdOBBr" 705 | }, 706 | "source": [ 707 | "# **Denoising example**" 708 | ] 709 | }, 710 | { 711 | "cell_type": "code", 712 | "execution_count": 0, 713 | "metadata": { 714 | "colab": {}, 715 | "colab_type": "code", 716 | "id": "xR4oH_QXII0v" 717 | }, 718 | "outputs": [], 719 | "source": [ 720 | "noise_factor = 0.5\n", 721 | "x_train_noisy = x_train + noise_factor * np.random.normal(loc=0.0, scale=1.0, size=x_train.shape) \n", 722 | "x_test_noisy = x_test + noise_factor * np.random.normal(loc=0.0, scale=1.0, size=x_test.shape) \n", 723 | "\n", 724 | "x_train_noisy = np.clip(x_train_noisy, 0., 1.)\n", 725 | "x_test_noisy = np.clip(x_test_noisy, 0., 1.)" 726 | ] 727 | }, 728 | { 729 | "cell_type": "code", 730 | "execution_count": 155, 731 | "metadata": { 732 | "colab": { 733 | "base_uri": "https://localhost:8080/", 734 | "height": 72 735 | }, 736 | "colab_type": "code", 737 | "id": "TvS9CX6III3b", 738 | "outputId": "8f54b173-159d-4c77-edac-15de211e6731" 739 | }, 740 | "outputs": [ 741 | { 742 | "name": "stdout", 743 | "output_type": "stream", 744 | "text": [ 745 | "Train on 60000 samples, validate on 10000 samples\n", 746 | "Epoch 1/1\n", 747 | "60000/60000 [==============================] - 20s 333us/step - loss: 0.1180 - val_loss: 0.1100\n" 748 | ] 749 | } 750 | ], 751 | "source": [ 752 | "cnn_hist = model_cnn.fit(x_train_noisy, x_train, validation_data=(x_test_noisy, x_test))" 753 | ] 754 | }, 755 | { 756 | "cell_type": "code", 757 | "execution_count": 0, 758 | "metadata": { 759 | "colab": {}, 760 | "colab_type": "code", 761 | "id": "HCRmI7oUI4jd" 762 | }, 763 | "outputs": [], 764 | "source": [ 765 | "reconstruct = model_cnn.predict(x_test_noisy)\n", 766 | "encoded_images= encoder.predict(x_test_noisy)" 767 | ] 768 | }, 769 | { 770 | "cell_type": "code", 771 | "execution_count": 163, 772 | "metadata": { 773 | "colab": { 774 | "base_uri": "https://localhost:8080/", 775 | "height": 131 776 | }, 777 | "colab_type": "code", 778 | "id": "gyehz6t-II5d", 779 | "outputId": "4de1e821-dc81-40b2-e614-9ada9ffacec7" 780 | }, 781 | "outputs": [ 782 | { 783 | "data": { 784 | "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlMAAAByCAYAAAB3LlRSAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nixES7WdaAAAAAElFTkSuQmCC\n", 785 | "text/plain": [ 786 | "
" 787 | ] 788 | }, 789 | "metadata": { 790 | "tags": [] 791 | }, 792 | "output_type": "display_data" 793 | } 794 | ], 795 | "source": [ 796 | "def plot_imgs_for_cnn_noisy(index=0):\n", 797 | " f = plt.figure(figsize=(10, 10))\n", 798 | " f.add_subplot(1,6, 1)\n", 799 | " plt.imshow(x_test_noisy[index].reshape(28, 28))\n", 800 | " \n", 801 | " \n", 802 | " f.add_subplot(1,6, 2)\n", 803 | " plt.imshow(encoded_images[index][:, :, 0])\n", 804 | " f.add_subplot(1,6, 3)\n", 805 | " plt.imshow(encoded_images[index][:, :, 1])\n", 806 | " f.add_subplot(1,6, 4)\n", 807 | " plt.imshow(encoded_images[index][:, :, 2])\n", 808 | " f.add_subplot(1,6, 5)\n", 809 | " plt.imshow(encoded_images[index][:, :, 3])\n", 810 | " \n", 811 | " \n", 812 | " f.add_subplot(1,6, 6)\n", 813 | " plt.imshow(reconstruct[index].reshape(28,28))\n", 814 | " \n", 815 | " plt.show(block=True)\n", 816 | " \n", 817 | "plot_imgs_for_cnn_noisy(3)" 818 | ] 819 | }, 820 | { 821 | "cell_type": "code", 822 | "execution_count": 0, 823 | "metadata": { 824 | "colab": {}, 825 | "colab_type": "code", 826 | "id": "X5KNaod4JLaX" 827 | }, 828 | "outputs": [], 829 | "source": [] 830 | } 831 | ], 832 | "metadata": { 833 | "accelerator": "GPU", 834 | "colab": { 835 | "collapsed_sections": [], 836 | "include_colab_link": true, 837 | "name": "DeepAutoencoder.ipynb", 838 | "provenance": [] 839 | }, 840 | "kernelspec": { 841 | "display_name": "Python 3", 842 | "language": "python", 843 | "name": "python3" 844 | }, 845 | "language_info": { 846 | "codemirror_mode": { 847 | "name": "ipython", 848 | "version": 3 849 | }, 850 | "file_extension": ".py", 851 | "mimetype": "text/x-python", 852 | "name": "python", 853 | "nbconvert_exporter": "python", 854 | "pygments_lexer": "ipython3", 855 | "version": "3.7.4" 856 | } 857 | }, 858 | "nbformat": 4, 859 | "nbformat_minor": 1 860 | } 861 | --------------------------------------------------------------------------------