added my data ML test

JR_day2_tensorflow/checkpoint

@@ -0,0 +1,2 @@
+model_checkpoint_path: "weights"
+all_model_checkpoint_paths: "weights"

JR_day2_tensorflow/lidoML_TF.py

@@ -0,0 +1,128 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Thu Jan 23 09:59:50 2020
+
+@author: tanu
+"""
+#%%
+# LIDO ML: tensorflow
+#%%
+
+from sklearn.datasets import load_boston
+from sklearn.pipeline import Pipeline
+from sklearn.preprocessing import MinMaxScaler
+import jrpytensorflow
+import tensorflow as tf
+
+import matplotlib.pyplot as plt
+
+boston = load_boston()
+#X, y = boston.data, boston.target
+
+
+from sklearn.model_selection import train_test_split
+
+from sklearn.datasets import load_digits
+
+digits = load_digits()
+
+X_train, X_test, y_train, y_test = train_test_split(
+        X, y, test_size = 0.2
+)
+#%%
+# P1
+X,y = jrpytensorflow.datasets.load_circles() 
+
+plt.figure()
+plt.scatter(X[:,0], X[:,1], c = y, edgecolor = 'black')
+
+#2)
+from sklearn.model_selection import train_test_split
+
+X_train, X_test, y_train, y_test = train_test_split(
+        X, y, test_size = 0.2
+)
+
+
+preprocess = Pipeline(
+        steps = [
+              ('rescale', MinMaxScaler())
+              ]
+)
+
+preprocess.fit(X_train)
+
+X_train = preprocess.transform(X_train)
+X_test = preprocess.transform(X_test)
+
+import tensorflow as tf
+logModel = tf.keras.models.Sequential([
+        tf.keras.layers.Dense(1, activation = 'sigmoid')
+        
+])
+
+logModel.compile(optimizer = 'sgd',
+                 loss = 'binary_crossentropy')
+history = logModel.fit(X, y, epochs = 100)
+
+logModel.summary()
+
+
+#4) predicted probability: for X
+model(X) # tf object
+model.predict(X) # array
+
+
+model(X).numpy().ravel() > 0.5
+
+sum(model(X).numpy().ravel() > 0.5)
+#101
+
+sum( ( model(X).numpy().ravel() > 0.5) == y)
+#97
+
+# 4*) predicted probability: for X_test
+
+logModel.compile(optimizer = 'sgd',
+                 loss = 'binary_crossentropy')
+history = logModel.fit(X_test, y_test, epochs = 100)
+
+logModel.summary()
+
+
+
+model(X_test) # tf object
+model.predict(X_test) # array
+
+
+model(X_test).numpy().ravel() > 0.5
+
+sum( model(X_test).numpy().ravel() > 0.5) 
+#22
+
+sum((model(X_test).numpy().ravel() > 0.5)  == y_test)
+#21
+
+#%%
+# Practical 2
+#%%
+
+from tensorflow import keras
+
+def smallModel():
+    model = tf.keras.models.Sequential([
+            tf.keras.layers.Dense(20, activation = 'relu'),
+            tf.keras.layers.Dense(10, activation = 'relu'),
+            tf.keras.layers.Dense(1, activation = 'softmax')
+            ])
+    model.compile(optimizer = 'sgd',
+                  loss = 'binary_crossentropy',
+                  metrics = ['accuracy'])
+
+    return model
+
+model = smallModel()
+model.summary()
+
+

JR_day2_tensorflow/lidoML_TF_D2.py

@@ -0,0 +1,261 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Thu Jan 23 09:59:50 2020
+
+@author: tanu
+"""
+#%%
+# LIDO ML: tensorflow
+#%%
+from sklearn.datasets import load_boston
+from sklearn.pipeline import Pipeline
+from sklearn.preprocessing import MinMaxScaler
+import jrpytensorflow
+import tensorflow as tf
+from sklearn.model_selection import train_test_split
+from tensorflow import keras
+import matplotlib.pyplot as plt
+from sklearn.model_selection import train_test_split
+from sklearn.datasets import load_digits
+from sklearn.preprocessing import LabelBinarizer
+import numpy as np
+#load_ext tensorboard
+#%%
+#def numModel(input_size, output_size):
+#    model = tf.keras.models.Sequential([
+#            tf.keras.layers.Dense(20, 
+#                                  input_shape = (input_size,), activation = 'relu'),
+#            tf.keras.layers.Dense(output_size, activation = 'softmax')
+#            ])
+#    model.compile(optimizer = 'sgd',
+#                  loss = 'categorical_crossentropy',
+#                  metrics = ['accuracy'])
+
+#    return model
+
+# load data
+digits = load_digits()
+
+X, y = digits.data, digits.target
+
+# split into training and test
+X_train, X_test, y_train, y_test = train_test_split(
+    X, y, test_size = 0.2
+    )
+
+prep = LabelBinarizer()
+y_train_bin = prep.fit_transform(y_train)
+y_test_bin = prep.transform(y_test)
+
+#%%
+#Practical 3
+
+X_train, y_train, X_test, y_test, labels = jrpytensorflow.datasets.load_fashion_mnist()
+
+# flatten the array which currently is 60000, 28, 28
+
+def numModel(input_size, output_size):
+    model = tf.keras.models.Sequential([
+        keras.layers.Flatten(input_shape = (28, 28)),
+        tf.keras.layers.Dense(20, #no of perceptron
+                                  input_shape = (input_size,), activation = 'relu'),
+        tf.keras.layers.Dense(output_size, activation = 'softmax')
+            ])
+    model.compile(optimizer = 'sgd',
+                  loss = 'sparse_categorical_crossentropy',
+                  metrics = ['accuracy'])
+
+    return model
+
+
+# call model
+model = numModel(784, 10)
+
+# call fit
+model.fit(X_train, y_train, epochs = 10)
+
+# check loss and accuracy
+loss, acc = model.evaluate(X_test, y_test, verbose = 0)
+print('test accuracy', acc)
+print('Loss',loss)
+
+
+# print predictions
+pred = model.predict(X_test)
+pred[0]
+
+import numpy as np
+print('prediction:', np.argmax(pred[0]))
+
+# change optimisers
+def numModel(input_size, output_size):
+    model = tf.keras.models.Sequential([
+        keras.layers.Flatten(input_shape = (28, 28)),
+        tf.keras.layers.Dense(20, #no of perceptron
+                                  input_shape = (input_size,), activation = 'relu'),
+        tf.keras.layers.Dense(output_size, activation = 'softmax')
+            ])
+    model.compile(optimizer = 'adam',
+              loss = 'sparse_categorical_crossentropy',
+              metrics = ['accuracy'])
+    return model
+
+
+# call model
+model = numModel(784, 10)
+
+# call fit
+model.fit(X_train, y_train, epochs = 10)
+
+# check loss and accuracy
+loss, acc = model.evaluate(X_test, y_test, verbose = 0)
+print('test accuracy', acc)
+print('Loss',loss)
+
+
+# print predictions
+pred = model.predict(X_test)
+pred[0]
+
+import numpy as np
+print('prediction:', np.argmax(pred[0]))
+print('truth:', y_test[0])
+
+model.save('entireModel.h5')
+entireModel = tf.keras.models.load_model('entireModel.h5')
+entireModel.summary()
+
+
+model.save_weights('./weights')
+
+model = numModel(784, 10)
+
+model.load_weights('./weights')
+
+# check loss and accuracy
+loss, acc = model.evaluate(X_test, y_test, verbose = 0)
+print('Restored test accuracy', acc)
+print('Reestored Loss',loss)
+
+
+callback = tf.keras.callbacks.ModelCheckpoint(
+    filepath = './checkpointPath',
+    save_weights_only = True,
+    verbose = 1
+    
+    )
+
+model.fit(X_train, y_train, epochs = 10,
+          callbacks = [callback])
+
+
+modell = numModel(784, 10)
+loss, acc = model.evaluate(X_test, y_test, verbose = 0)
+print('No checkpoint Test loss :', loss)
+
+
+model = numModel(784, 10)
+model.load_weights('./checkpointPath')
+loss, acc = model.evaluate(X_test, y_test, verbose = 0)
+print('With checkpoint Test loss :', loss)
+
+#%%
+# Visualisation
+#%%
+
+#load_ext tensorboard
+
+tensorBoardCallback = keras.callbacks.TensorBoard( log_dir = "logs/fit")
+
+model = numModel(784, 10)
+model.fit(X_train, y_train, epochs = 10,
+          validation_data = (X_test, y_test),
+          callbacks = [tensorBoardCallback])
+
+##tensorboard --logdir logs
+
+#%%
+#%Practical 4
+#%%
+
+walking = jrpytensorflow.datasets.load_walking()
+
+#import matplotlib.pyplot as plt
+#import numpy as np
+
+sub = walking[walking['sample'] == 400]
+sub['time'] = np.arange(260)
+
+fig, (ax1, ax2, ax3) = plt.subplots(1, 3, figsize = (18, 10))
+sub.plot(x = 'time', y = 'acc_x', ax = ax1)
+sub.plot(x = 'time', y = 'acc_y', ax = ax2)
+sub.plot(x = 'time', y = 'acc_z', ax = ax3)
+plt.show()
+
+dims = ['acc_x', 'acc_y', 'acc_z']
+#x = np.dstack([walking[[d]].values.reshape(-1,260) for d in dims])
+X = np.dstack([walking[[d]].values.reshape(-1,260) for d in dims])
+y = walking['person'].values[::260] - 1
+
+
+# load data
+# split into training and test
+X_train, X_test, y_train, y_test = train_test_split(
+    X, y, test_size = 0.2
+    )
+
+# Binarise labels
+    X, y, test_size = 0.2
+    )
+prep = LabelBinarizer()
+y_train_bin = prep.fit_transform(y_train)
+y_test_bin = prep.transform(y_test)
+
+# normalise
+#X_train, X_test = X_train / 255.0, X_test / 255.0
+
+
+# model architecture
+from tensorflow.keras.optimizers import Adam
+
+def convModel():
+    model = tf.keras.models.Sequential ([
+        tf.keras.layers.Conv1D (6, 4,
+                                activation = 'relu', input_shape = (260,3)),
+        
+        tf.keras.layers.MaxPooling1D(2),
+        
+        tf.keras.layers.Conv1D(16, 3, activation = 'relu'),
+        tf.keras.layers.Flatten(),# model architecture
+
+        tf.keras.layers.Dense (150, activation = 'relu'),
+        tf.keras.layers.Dense(50, activation = 'relu'),
+        tf.keras.layers.Dense(15, activation = 'softmax')
+    ])
+    
+    opt = Adam(lr = 0.001)
+    
+    model.compile(optimizer = opt,
+                  loss = 'categorical_crossentropy', # sparse for non-binarised labels
+                  metrics = ['accuracy'])
+    
+    return model
+        
+model = convModel()
+history = model.fit(X_train, y_train_bin, epochs = 10, 
+                    validation_data = (X_test, y_test_bin))       
+
+historyDict = history.history
+
+# check loss and accuracy
+loss, acc = model.evaluate(X_test, y_test_bin,  verbose = 0)
+print('test accuracy', acc)
+print('Loss',loss)
+
+# image for P4: Refer to Page 10 from notes
+## Notes: Check the dim of your data
+# dim of your filter MUST be the same as the dim of your data
+
+
+ 

JR_day2_tensorflow/my_notes

@@ -0,0 +1,23 @@
+#==============================
+# Date: 23rd January 2020
+# LIDO ML: Tensorflow training
+# Day 1
+#==============================
+v2: Tensorflow	
+	pytorch
+		keras
+
+# Ben
+Wiki and neofetch
+
+# Training and Test sets
+nobs can be different 
+BUT 
+nfeatures should say the same between training and test sets
+
+# Book
+Goodfellow book on ML
+
+# Pej
+XGBoost: python library that does Random Forst, Decision trees, etc...(possibly instead of?!)
+Lido ML meeting: Friday, 31st Jan in B62, 10-12 @Birkbeck