I recently got a Nvidia Card and wanted to try LSTM-Models with the new GPU-Support. Sadly I do not know much about LSTMs. And I build this little model to test it:
import pandas as pd
from keras.models import Sequential
from keras.layers import Dense, LSTM, Dropout
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import Normalizer, StandardScaler
import tensorflow as tf
from keras.backend.tensorflow_backend import set_session
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
config.gpu_options.visible_device_list = "0"
set_session(tf.Session(config=config))
data = pd.read_excel("./data/google_data.xlsx", header=0)
X = data.drop("Close", axis=1)
y = data["Close"]
model = Sequential()
model.add(LSTM(units=10, activation='sigmoid', input_shape=(4,1),return_sequences=True))
model.add(Dropout(0.4))
model.add(Dense(10, activation="sigmoid"))
model.add(Dense(1, activation="sigmoid"))
model.compile(optimizer='adam', loss='mean_squared_error')
print(model.summary())
normalizer = StandardScaler()
normalizer.fit(X)
X = normalizer.fit_transform(X)
X_train, y_train, X_test, y_test = train_test_split(X, y, test_size=0.20, shuffle=False)
model.fit(X, y, batch_size=64, epochs=40, verbose=1, validation_data=(X_test, y_test))
I always get an ValueError, I have tried the Inputshape from the Keras Docs w ith (batch_size,timesteps,features) but I still get the same ValueError.
I guess it is probably a quite dumb problem, but a newbie like me could need some help. Thanks!
Related
I want to get KerasRegressor history but all the time I get (...) object has no attribute 'History'
'''
# Regression Example With Boston Dataset: Standardized and Wider
import numpy as np
from pandas import read_csv
from keras.models import Sequential
from keras.layers import Dense
#from keras.wrappers.scikit_learn import KerasRegressor
from scikeras.wrappers import KerasRegressor
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import KFold
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
import keras.backend as K
# load dataset
dataframe = read_csv("Data 1398-2.csv")
dataset = dataframe.values
# split into input (X) and output (Y) variables
X = dataset[:,0:10]
Y = dataset[:,10]
############
from sklearn import preprocessing
from sklearn.metrics import r2_score
min_max_scaler = preprocessing.MinMaxScaler()
X_scale = min_max_scaler.fit_transform(X)
from sklearn.model_selection import train_test_split
X_train, X_val_and_test, Y_train, Y_val_and_test = train_test_split(X_scale, Y, test_size=0.25)
X_val, X_test, Y_val, Y_test = train_test_split(X_val_and_test, Y_val_and_test, test_size=0.55)
##################
# define wider model
def wider_model():
# create model
model = Sequential()
model.add(Dense(40, input_dim=10, kernel_initializer='normal', activation='relu'))
model.add(Dense(20, kernel_initializer='normal', activation='relu'))
model.add(Dense(1, kernel_initializer='normal'))
# Compile model
model.compile(loss='mean_squared_error',metrics=['mae'], optimizer='adam')
#history = model.fit(X, Y, epochs=10, batch_size=len(X), verbose=1)
return model
# evaluate model with standardized dataset
from keras.callbacks import History
estimators = []
estimators.append(('standardize', StandardScaler()))
estimators.append(('mlp',KerasRegressor(model=wider_model, epochs=100, batch_size=2, verbose=0) ))
pipeline = Pipeline(estimators)
kfold = KFold(n_splits=5)
results = cross_val_score(pipeline, X_train, Y_train, cv=kfold)
print("Wider: %.2f (%.2f) MSE" % (results.mean(), results.std()))
import matplotlib.pyplot as plt
#plt.plot(history.history['loss'])
#plt.plot(history.history['val_loss'])
#plt.title('Model loss')
#plt.ylabel('Loss')
#plt.xlabel('Epoch')
#plt.legend(['Train', 'Val'], loc='upper right')
#plt.show()
'''
Model is at index 1 in your case, but you can also find it. Now to get history object:
pipeline.steps[1][1].model.history.history
If you are sure that Keras Model is always the last estimator, you can also use:
pipeline._final_estimator.model.history.history
I have the following NN model using Keras:
import numpy as np
from keras import Sequential
from keras.layers import Dense
path = 'pima-indians-diabetes.data.csv'
dataset = np.loadtxt(path, delimiter=",")
X = dataset[:,0:8]
Y = dataset[:,8]
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.2)
model = Sequential()
model.add(Dense(16, input_dim=8, activation='relu'))
model.add(Dense(32, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
model.fit(X_train, y_train, epochs=100, batch_size=16, validation_data=(X_test, y_test))
Kindly, is it possible to extract the confusion matrix? How?
You can use scikit-learn:
y_pred = model.predict(X_test)
confusion_matrix = sklearn.metrics.confusion_matrix(y_test, np.rint(y_pred))
It can be done using TensorFlow (which is almost Keras =)).
You start by making predictions on your test set with your trained model:
predictions = model.predict(x_test)
Then you can import TensorFlow and use its confusion_matrix method as follows.
import tensorflow as tf
conf_matrix = tf.math.confusion_matrix(labels=y_test,
predictions=predictions)
More information in the TensorFlow documentation.
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation
from keras.optimizers import SGD
from keras.datasets import mnist
import numpy
model = Sequential()
model.add(Dense(500,input_shape=(784,))) # 28*28=784
model.add(Activation('tanh')) # tanh
model.add(Dropout(0.5)) # 50% dropout
model.add(Dense(500)) # 500个
model.add(Activation('tanh'))
model.add(Dropout(0.5))
model.add(Dense(10))
model.add(Activation('softmax'))
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd, class_mode='categorical')
(X_train, y_train), (X_test, y_test) = mnist.load_data()
X_train = X_train.reshape(X_train.shape[0], X_train.shape[1] * X_train.shape[2])
X_test = X_test.reshape(X_test.shape[0], X_test.shape[1] * X_test.shape[2])
Y_train = (numpy.arange(10) == y_train[:, None]).astype(int)
Y_test = (numpy.arange(10) == y_test[:, None]).astype(int)
model.fit(X_train,Y_train,batch_size=200,epochs=50,shuffle=True,verbose=0,validation_split=0.3)
model.evaluate(X_test, Y_test, batch_size=200, verbose=0)
print("test set")
scores = model.evaluate(X_test,Y_test,batch_size=200,verbose=0)
print("")
print("The test loss is %f" % scores)
result = model.predict(X_test,batch_size=200,verbose=0)
I found this post Error when profiling keras models, which modifies the tensorflow library.
So, I checked Keras library code from the link. But could not find anything like ['class_mode'] to modify the keras library. Next, I tried running the code after re-installing keras, but even that didn't work.
I used anaconda to import Kreas， maybe I install wrong?
Can anyone suggest a solution for this?
remove class_mode='categorical',it runs
I am newbie on keras,
I try to follow the Keras tutorial for Multilayer Perceptron (MLP) for multi-class softmax classification, using my data set.
My data has 3 classes and only one feature, but I don't understand why the result always show just 0,3 of accuracy and the model predicted all training data as first class. then the confusion matrix is like this.
Confusion matrix
Here the coding:
import keras
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation
from keras.optimizers import SGD
import pandas as pd
import numpy as np
# Importing the dataset
dataset = pd.read_csv('StatusAll.csv')
X = dataset.iloc[:, 1:].values
y = dataset.iloc[:, 0:1].values
# Splitting the dataset into the Training set and Test set
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, random_state = 0)
from keras.utils import to_categorical
y_train = to_categorical(y_train)
y_test = to_categorical(y_test)
model = Sequential()
# Dense(64) is a fully-connected layer with 64 hidden units.
# in the first layer, you must specify the expected input data shape:
# here, 20-dimensional vectors.
model.add(Dense(64, activation='tanh', input_dim=1))
model.add(Dropout(0.5))
model.add(Dense(64, activation='tanh'))
model.add(Dropout(0.5))
model.add(Dense(4, activation='softmax'))
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy',
optimizer=sgd,
metrics=['accuracy'])
history = model.fit(x_train, y_train,
epochs=100,
batch_size=128)
score = model.evaluate(x_test, y_test, batch_size=128)
print('Test score:', score[0])
print('Test accuracy:', score[1])
from sklearn import metrics
prediction = model.predict(x_test)
prediction = np.around(prediction)
y_test_non_category = [ np.argmax(t) for t in y_test ]
y_predict_non_category = [ np.argmax(t) for t in prediction ]
from sklearn.metrics import confusion_matrix
conf_mat = confusion_matrix(y_test_non_category, y_predict_non_category)
print (conf_mat)
I hope I can get some advice, thanksss.
The x_train example
x_train
y_train before converted to categorical
enter image description here
Your final Dense layer has 4 outputs, it seems like you are classifying 4 instead of 3.
model.add(Dense(3, activation='softmax')) # Number of classes 3
It would be helpful to see sample data from x_train and y_train to make sure the pre-processing is correct. Because you have only 1 feature, a MLP might be overkill. A decision tree would be simpler unless you want to experiment with MLPs.
The problem with this code is that I am giving classifier,
One hot encoded data:
Means:
X-train, X-test, y_train, y_test is one hot encoded.
But the classifier is predicting the output:
y_pred_test, y_pred_train in Numerical form
(which I think is incorrect as well). Can anyone help with this?
This is a dummy example so no concern over low accuracy but just to know why it's predicting the output in not One Hot encoded form.
Thanks !
# -*- coding: utf-8 -*-
import numpy as np
import pandas as pd
x=pd.DataFrame()
x['names']= np.arange(1,10)
x['Age'] = np.arange(1,10)
y=pd.DataFrame()
y['target'] = np.arange(1,10)
from sklearn.preprocessing import OneHotEncoder, Normalizer
ohX= OneHotEncoder()
x_enc = ohX.fit_transform(x).toarray()
ohY = OneHotEncoder()
y_enc = ohY.fit_transform(y).toarray()
print (x_enc)
print("____")
print (y_enc)
import keras
from keras import regularizers
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.models import load_model
from keras.layers.advanced_activations import LeakyReLU
marker="-------"
from keras.wrappers.scikit_learn import KerasClassifier
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import train_test_split
def create_model(learn_rate=0.001):
model = Sequential()
model.add(Dense(units = 15, input_dim =18,kernel_initializer= 'normal', activation="tanh"))
model.add(Dense(units=9, activation = "softmax"))
model.compile(loss="categorical_crossentropy", optimizer="adam", metrics=['accuracy'])
return model
if __name__=="__main__":
X_train, X_test, y_train, y_test = train_test_split(x_enc, y_enc, test_size=0.33, random_state=42)
print ("\n\n",marker*5," Classification\nX_train shape is: ",X_train.shape,"\tX_test shape is:",X_test.shape)
print ("\ny_train shape is: ",y_train.shape,"\t y_test shape is:",y_test.shape,"\n\n")
norm = Normalizer()
#model
X_train = norm.fit_transform(X_train)
X_test = norm.transform(X_test)
earlyStopping=keras.callbacks.EarlyStopping(monitor='val_loss', patience=0, verbose=0, mode='auto')
model = KerasClassifier(build_fn=create_model, verbose=0)
fit_params={'callbacks': [earlyStopping]}
#grid
# batch_size =[50,100,200, 300,400]
epochs = [2,5]
learn_rate=[0.1,0.001]
param_grid = dict( epochs = epochs, learn_rate = learn_rate)
grid = GridSearchCV(estimator = model, param_grid = param_grid, n_jobs=1)
#Predicting
print (np.shape(X_train), np.shape(y_train))
y_train = np.reshape(y_train, (-1,np.shape(y_train)[1]))
print ("y_train shape after reshaping", np.shape(y_train))
grid_result = grid.fit(X_train, y_train, callbacks=[earlyStopping])
print ("grid score using params: ", grid_result.best_score_, " ",grid_result.best_params_)
#scores
print("SCORES")
print (grid_result.score(X_test,y_test))
# summarize results
#print("Best: %f using %s" % (grid_result.best_score_, grid_result.best_params_))
#means = grid_result.cv_results_['mean_test_score']
#stds = grid_result.cv_results_['std_test_score']
#params = grid_result.cv_results_['params']
#for mean, stdev, param in zip(means, stds, params):
# print("%f (%f) with: %r" % (mean, stdev, param))
print("\n\n")
print("y_test is",y_test)
y_hat_test = grid.predict(X_test)
y_hat_train = grid.predict(X_train)
print("y_hat_test is ", y_hat_test)