We Keep Coding

Convolutional Neural Network - 1D - Feature Classification Error

I am trying to modify the following example to simulate CNN for my set of data and running into some errors
https://machinelearningmastery.com/cnn-models-for-human-activity-recognition-time-series-classification/
X = D.replace(['Resting', 'Swimming', 'Feeding', 'Non directed motion'], [0, 1, 2, 3])
X_Label = X['Label'].to_numpy()
X_Data = X[['X_static','Y_static','Z_static','X_dynamic','Y_dynamic','Z_dynamic']].to_numpy()
X_names = ['X_static','Y_static','Z_static','X_dynamic','Y_dynamic','Z_dynamic']
X_Label_Names = np.array(['Resting', 'Swimming', 'Feeding', 'Non directed motion'])
X_Data is a 5600 by 6 column numpy matrix. Each column represents a type of measurement data over time
X_Label is a 5600 by 1 column consisting of values of 0 through 3 that represents the features or attributes. 0 represents resting, 1 represents swimming and so on.
X = X_Data
y = X_Label
def load_dataset_f(X,y):
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.5, stratify=y, random_state=random_state
)
trainX = X_train
trainy = y_train
testX = X_test
testy = y_test
print(trainX)
print(trainX.shape)
print(trainy.shape)
return trainX, trainy, testX, testy
# fit and evaluate a model
def evaluate_model_f(trainX, trainy, testX, testy):
verbose, epochs, batch_size = 2, 10, 20
n_timesteps, n_features, n_outputs = 6, 1, 1
print('n timesteps --------------------------------------------------------------------')
print(n_timesteps)
model = Sequential()
model.add(Conv1D(filters=64, kernel_size=3, activation='relu', input_shape=(n_timesteps,n_features)))
model.add(Conv1D(filters=64, kernel_size=3, activation='relu'))
model.add(Dropout(0.5))
model.add(MaxPooling1D(pool_size=2))
model.add(Flatten())
model.add(Dense(100, activation='relu'))
model.add(Dense(n_outputs, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
# fit network
print(to_categorical(trainy))
model.fit(trainX.reshape(len(trainX),6,1), to_categorical(trainy))
# evaluate model
_, accuracy = model.evaluate(testX, testy, batch_size=batch_size, verbose=0)
return accuracy
def run_experiment_f(repeats=1):
# load data
trainX, trainy, testX, testy = load_dataset_f(X,y)
print(trainX)
# repeat experiment
scores = list()
for r in range(repeats):
score = evaluate_model_f(trainX, trainy, testX, testy)
score = score * 100.0
print('>#%d: %.3f' % (r+1, score))
scores.append(score)
# summarize results
summarize_results(scores)
load_dataset_f(X,y)
run_experiment_f()
I am unfamiliar with the tensorflow library and getting errors at model.fit(), I am not sure to how to approach this. The matrix presented in the example was 3D where as my data is 2D, not sure if that matters. How do I get this code to work ?

You need to make sure that your input to your Conv1D layer has the shape (timesteps, features) and that your last output layer's units equals the number of unique labels in your dataset. Here is a working example:
import tensorflow as tf
trainX = tf.random.normal((32, 6))
trainy = tf.random.uniform((32, 1), maxval=4)
verbose, epochs, batch_size = 2, 10, 20
n_timesteps, n_features, n_outputs = 6, 1, 4
print('n timesteps --------------------------------------------------------------------')
print(n_timesteps)
model = tf.keras.Sequential()
model.add(tf.keras.layers.Conv1D(filters=64, kernel_size=3, activation='relu', input_shape=(n_timesteps,n_features)))
model.add(tf.keras.layers.Conv1D(filters=64, kernel_size=3, activation='relu'))
model.add(tf.keras.layers.Dropout(0.5))
model.add(tf.keras.layers.MaxPooling1D(pool_size=2))
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(100, activation='relu'))
model.add(tf.keras.layers.Dense(n_outputs, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
# fit network
print(tf.keras.utils.to_categorical(trainy))
trainX = tf.expand_dims(trainX, axis=2)
model.fit(trainX, tf.keras.utils.to_categorical(trainy))

ValueError: Shapes are incompatible in LSTM model

I am creating an LSTM model based on the following parameters
embed_dim = 128
lstm_out = 200
batch_size = 32
model = Sequential()
model.add(Embedding(2500, embed_dim,input_length = X.shape[1]))
model.add(Dropout(0.2))
model.add(LSTM(lstm_out))
model.add(Dense(2,activation='sigmoid'))
model.compile(loss = 'categorical_crossentropy', optimizer='adam',metrics = ['accuracy'])
print(model.summary())
Xtrain, Xtest, ytrain, ytest = train_test_split(X, train['target'], test_size = 0.2, shuffle=True)
print(Xtrain.shape, ytrain.shape)
print(Xtest.shape, ytest.shape)
model.fit(Xtrain, ytrain, batch_size =batch_size, epochs = 1, verbose = 5)
but I am receiving the following error
ValueError: Shapes (32, 1) and (32, 2) are incompatible
Can you help me with this error?

Your y_train is coming from a single column of a Pandas dataframe, which is a single column. This is suitable if your classification problem is a binary classification 0/1 problem. Then you only need a single neuron in the output layer.
model = Sequential()
model.add(Embedding(2500, embed_dim,input_length = X.shape[1]))
model.add(Dropout(0.2))
model.add(LSTM(lstm_out))
# Only one neuron in the output layer
model.add(Dense(1,activation='sigmoid'))

data shape mismatch in time series prediction

working with a LSTM model for predicting stock prices, i did every step exactly as the tutorial but unlike the tutorial, my code runs into an error.
here is the code i am working with:
df = pd.read_csv(f'D:\\algo\\all\\EURUSD_15M.csv')
df = df.loc[:, ~df.columns.str.contains('^Unnamed',)]
training_set = df.iloc[:-int(len(df)/10), 4:5].values
sc = MinMaxScaler(feature_range= (0, 1))
training_set_scaled = sc.fit_transform(training_set)
x_train , y_train = [], []
for i in range(60, len(training_set)):
x_train.append(training_set_scaled[i-60:i, 0])
y_train.append(training_set_scaled[i, 0])
x_train, y_train = np.array(x_train), np.array(y_train)
x_train = np.reshape(x_train, (x_train.shape[0], x_train.shape[1], 1))
model = Sequential()
model.add(LSTM(units=50, return_sequences=True, input_shape = (x_train.shape[1],1)))
model.add(Dropout(0.2))
model.add(LSTM(units=50, return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(units=50, return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(units=50, return_sequences=True))
model.add(Dropout(0.2))
model.add(Dense(units=1))
model.compile(optimizer='adam', loss='mean_squared_error', metrics=['Accuracy'])
model.fit(x_train, y_train, epochs=5, batch_size=64)
So whats supposed to happen is take 60 periods of a price and predict the 61th period.
but i ultimately face the following error:
ValueError: A target array with shape (379319, 1) was passed for an output of shape (None, 60, 1) while using as loss `mean_squared_error`. This loss expects targets to have the same shape as the output.
what am i doing wrong?

As a dataset try using
TimeseriesGenerator (tf.keras.preprocessing.sequence.TimeseriesGenerator) instead of your custom list -> https://www.tensorflow.org/api_docs/python/tf/keras/preprocessing/sequence/TimeseriesGenerator
ex.
train_gen = TimeseriesGenerator(Xtrain, Xtrain, n_steps, batch_size=24*7)
valid_gen = TimeseriesGenerator(Xvalid, Xvalid, n_steps, batch_size=24*7)
test_gen = TimeseriesGenerator(Xtest, Xtest, n_steps, batch_size=24*7)

How to Reshape my data for CNN? ValueError: cannot reshape array of size 267 into shape (267,2)

#Input 13 features
#Output Binary
# 297 data points
x = x.iloc[:,[0,1,2,3,4,5,6,7,8,9,10,11,12]].values
y1= y['Target'}
# Stratified K fold cross Validation
kf = StratifiedKFold(n_splits=10,random_state=None)
num_features=13
num_predictions=2
#Splitting data
for train_index, test_index in kf.split(x,y1):
x_train, x_test = x[train_index], x[test_index]
y_train, y_test = y1[train_index], y1[test_index]
# Standardization of data
sc=StandardScaler(0,1)
X_train = sc.fit_transform(x_train)
X_test = sc.transform(x_test)
print(X_train.shape) # o/p: (267,13)
Print(y_train.shape) # o/p: (267)
X_train = X_train.reshape((X_train.shape[0], X_train.shape[1], -1))
X_test = X_test.reshape((X_test.shape[0], X_test.shape[1], -1))
# Convert class vectors to binary class matrices.
y_train = np.reshape(y_train, (y_train.shape[0], num_predictions))
y_test = np.reshape(y_test, (y_test.shape[0], num_predictions))
verbose, epochs, batch_size = 1, 10, 32
n_timesteps, n_features, n_outputs = X_train.shape[1],X_train.shape[2],y_train.shape[1]
model = Sequential()
model.add(Conv1D(filters=64, kernel_size=3, activation='relu', input_shape (n_timesteps,n_features)))
model.add(Conv1D(filters=64, kernel_size=3, activation='relu'))
model.add(Dropout(0.5))
model.add(MaxPooling1D(pool_size=2))
model.add(Flatten())
model.add(Dense(100, activation='relu'))
model.add(Dense(297, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
# fit network
model.fit(X_train, y_train, epochs=epochs, batch_size=batch_size, verbose=verbose)
# evaluate model
accuracy = model.evaluate(X_test, y_test, batch_size=batch_size, verbose=0)
print(accuracy)
How can i input data to feed into CNN which requires 3 dimensions of data. How to solve issue
ValueError: cannot reshape array of size 267 into shape (267,2).

Imagine you have a line of 100 squares, and you want to make it a rectangle. Could you turn it into a rectangle by making it 2x100? No, but you could make it 50x2.
In short, you can't make a rectangle that has more values than the original.

Very simple Keras binary classification doesn't work

Can someone please explain why the following code achieves only about 50% classification accuracy?
I am trying to classify lists of 20 items into 0 or 1. The lists are all 5s or all 6s.
import numpy as np
import keras
from sklearn.model_selection import train_test_split
positive_samples = [[5]*20]*100
negative_samples = [[6]*20]*100
x_list = np.array(positive_samples+negative_samples, dtype=np.float32)
y_list = np.array([1]*len(positive_samples)+[0]*len(negative_samples), dtype=np.float32)
x_train, x_test, y_train, y_test = train_test_split(x_list, y_list, test_size=0.20, random_state=42)
y_train = keras.utils.to_categorical(y_train, 2)
y_test = keras.utils.to_categorical(y_test, 2)
model = keras.models.Sequential()
model.add(keras.layers.Dense(10, input_dim=x_train.shape[1], kernel_initializer='normal', activation='relu'))
model.add(keras.layers.Dense(5, kernel_initializer='normal', activation='relu'))
model.add(keras.layers.Dense(2, kernel_initializer='normal', activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
model.fit(x_train, y_train, batch_size=10, epochs=20, verbose=2, validation_data=(x_test, y_test))
print (model.evaluate(x_test, y_test, verbose=0))

Since the last output layer has 2 values per sample, you need to use a softmax activation instead of sigmoid.
Also, that means binary_crossentropy cannot be used, and you have to use categorical_crossentropy.
I have also normalized the dataset x_list by dividing with the maximum (6).
x_list /= x_list.max()
Also, you need to shuffle the dataset, by passing shuffle=True in train_test_split.
import numpy as np
import keras
from sklearn.model_selection import train_test_split
positive_samples = [[5]*20]*100
negative_samples = [[6]*20]*100
x_list = np.array(positive_samples+negative_samples, dtype=np.float32)
y_list = np.array([1]*len(positive_samples)+[0]*len(negative_samples), dtype=np.float32)
x_list /= x_list.max()
x_train, x_test, y_train, y_test = train_test_split(x_list, y_list, test_size=0.20, shuffle=True, random_state=42)
y_train = keras.utils.to_categorical(y_train, 2)
y_test = keras.utils.to_categorical(y_test, 2)
model = keras.models.Sequential()
model.add(keras.layers.Dense(10, input_dim=x_train.shape[1], kernel_initializer='normal', activation='relu'))
model.add(keras.layers.Dense(5, kernel_initializer='normal', activation='relu'))
model.add(keras.layers.Dense(2, kernel_initializer='normal', activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
model.fit(x_train, y_train, batch_size=10, epochs=100, verbose=2, validation_data=(x_test, y_test))
print (model.evaluate(x_test, y_test, verbose=0))
A sigmoid activation in the output makes sense only when there is 1 output, in which the value would be in range [0, 1] signifying probability of the instance being a 1.
In case of 2 (or more) output neurons, it is necessary we normalize the probabilities to sum upto 1 so we use a softmax layer instead.

Data should be normalized before feeding it to the network, this is normally done by changing the values to be between 0 and 1 or -1 and 1. Setting the input to;
positive_samples = [[1]*20]*100
negative_samples = [[-1]*20]*100
works or the model could be changed to:
model = keras.models.Sequential()
model.add(BatchNormalization())
model.add(keras.layers.Dense(10, kernel_initializer='normal', activation='relu'))
model.add(keras.layers.Dense(5, kernel_initializer='normal', activation='relu'))
model.add(keras.layers.Dense(2, kernel_initializer='normal', activation='sigmoid'))