import pandas as pd
import matplotlib.pyplot as plt
import re
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import LSTM,Dense, Dropout, SpatialDropout1D
from tensorflow.keras.layers import Embedding
from tensorflow.keras.optimizers import Adam
from sklearn.model_selection import train_test_split
data = pd.read_csv("./emails.csv")
print(data.head())
data = data[['text','email_sentiment']]
data['text'] = data['text'].apply(lambda x: x.lower())
data['text'] = data['text'].apply((lambda x: re.sub('[^a-zA-z0-9\s]','',x)))
print(data.head())
max_fatures = 50000
max_seq_length = 250
tokenizer = Tokenizer(num_words=max_fatures,filters='!"#$%&()*+,-./:;<=>?#[\]^_`{|}~', lower=True)
tokenizer.fit_on_texts(data['text'].values)
word_index = tokenizer.word_index
X = tokenizer.texts_to_sequences(data['text'].values)
X = pad_sequences(X,maxlen=max_seq_length)
Y= pd.get_dummies(data['email_sentiment']).values
X_train,Y_train = train_test_split(X,Y, test_size = 0.10, random_state = 42)
embedding_vector_length = 100
lstm_out= 196
model = Sequential()
model.add(Embedding(max_fatures, embedding_vector_length, input_length=X.shape[1]))
model.add(SpatialDropout1D(0.2))
model.add(LSTM(100, dropout=0.2, recurrent_dropout=0.2))
model.add(Dense(3,activation='softmax'))
model.compile(loss='categorical_crossentropy',optimizer='adam',metrics=['accuracy'])
print(model.summary())
Error occured:
X_train,Y_train = train_test_split(X,Y, test_size = 0.10, random_state = 42)
ValueError: too many values to unpack (expected 2)
Unable to train X_train with the dataset due to value errors. The X_train value consist of various emails which are categorized to postive negative and neutral sentiment based on LSTM classes 3
Related
I got a ValueError when using TensorFlow to create a model. Based on the error there is a problem that occurs with the kernel regularizer applied on the Conv2D layer and the mean squared error function. I used the L1 regularizer provided by the TensorFlow keras package. I've tried setting different values for the L1 regularization factor and even setting the value to 0, but I get the same error.
Context: Creating a model that predicts phenotype traits given genotypes and phenotypes datasets. The genotype input data has 4276 samples, and the input shape that the model takes is (28220,1). My labels represent the phenotype data. The labels include 4276 samples with 20 as the number of phenotype traits in the dataset. In this model we use differential privacy(DP) and add it to a CNN model which uses the Mean squared error loss function and the DPKerasAdamOptimizer to add DP. I'm just wondering if MSE would be a good choice as a loss function?
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
!pip install tensorflow-privacy
import numpy as np
import tensorflow as tf
from tensorflow_privacy import *
import tensorflow_privacy
from matplotlib import pyplot as plt
import pylab as pl
import numpy as np
import pandas as pd
from tensorflow.keras.models import Model
from tensorflow.keras import datasets, layers, models, losses
from tensorflow.keras import backend as bke
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.regularizers import l1, l2, l1_l2 #meaning of norm
from sklearn import preprocessing
from sklearn.model_selection import train_test_split
batch_size = 32
epochs = 4
microbatches = 8
inChannel = 1
kr = 0#1e-5
num_kernels=8
drop_perc=0.25
dim = 1
l2_norm_clip = 1.5
noise_multiplier = 1.3
learning_rate = 0.25
latent_dim = 0
def print_datashape():
print('genotype data: ', genotype_data.shape)
print('phenotype data: ', single_pheno.shape)
genotype_data = tf.random.uniform([4276, 28220],1,3, dtype=tf.dtypes.int32)
phenotype_data = tf.random.uniform([4276, 20],-4.359688,34,dtype=tf.dtypes.float32)
genotype_data = genotype_data.numpy()
phenotype_data = phenotype_data.numpy()
small_geno = genotype_data
single_pheno = phenotype_data[:, 1]
print_datashape()
df = small_geno
min_max_scaler = preprocessing.MinMaxScaler()
df = min_max_scaler.fit_transform(df)
scaled_pheno = min_max_scaler.fit_transform(single_pheno.reshape(-1,1)).reshape(-1)
feature_size= df.shape[1]
df = df.reshape(-1, feature_size, 1, 1)
print("df: ", df.shape)
print("scaled: ", scaled_pheno.shape)
# split train to train and valid
train_data,test_data,train_Y,test_Y = train_test_split(df, scaled_pheno, test_size=0.2, random_state=13)
train_X,valid_X,train_Y,valid_Y = train_test_split(train_data, train_Y, test_size=0.2, random_state=13)
def print_shapes():
print('train_X: {}'.format(train_X.shape))
print('train_Y: {}'.format(train_Y.shape))
print('valid_X: {}'.format(valid_X.shape))
print('valid_Y: {}'.format(valid_Y.shape))
input_shape= (feature_size, dim, inChannel)
predictor = tf.keras.Sequential()
predictor.add(layers.Conv2D(num_kernels, (5,1), padding='same', strides=(12, 1), activation='relu', kernel_regularizer=tf.keras.regularizers.L1(kr),input_shape= input_shape))
predictor.add(layers.AveragePooling2D(pool_size=(2,1)))
predictor.add(layers.Dropout(drop_perc))
predictor.add(layers.Flatten())
predictor.add(layers.Dense(int(feature_size / 4), activation='relu'))
predictor.add(layers.Dropout(drop_perc))
predictor.add(layers.Dense(int(feature_size / 10), activation='relu'))
predictor.add(layers.Dropout(drop_perc))
predictor.add(layers.Dense(1))
mse = tf.keras.losses.MeanSquaredError(reduction=tf.keras.losses.Reduction.NONE)
optimizer = DPKerasAdamOptimizer(learning_rate=learning_rate, l2_norm_clip=l2_norm_clip, noise_multiplier=noise_multiplier, num_microbatches=microbatches)
# compile
predictor.compile(loss=mse, optimizer=optimizer, metrics=['mse'])
#summary
predictor.summary()
print_shapes()
predictor.fit(train_X, train_Y,batch_size=batch_size,epochs=epochs,verbose=1, validation_data=(valid_X, valid_Y))
ValueError: Shapes must be equal rank, but are 1 and 0
From merging shape 0 with other shapes. for '{{node AddN}} = AddN[N=2, T=DT_FLOAT](mean_squared_error/weighted_loss/Mul, conv2d_2/kernel/Regularizer/mul)' with input shapes: [?], [].
When I try to use the TimeSeriesGenerator function, my Keras LSTM NN starts training for a few moments but then gives a ValueError message. What's wrong? I wonder how it can start training and then get an error.
My similar implementation without this function runs smoothly but then the quality of the predictions are awful (and I'm not sure that this function, once successfully implemented, would make a difference).
See the code below:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from tensorflow.keras.models import Model
from tensorflow.keras.optimizers import Nadam
from tensorflow.keras.layers import Input, LSTM, Dense
from tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau, TerminateOnNaN
from tensorflow.keras.preprocessing.sequence import TimeseriesGenerator
data = pd.read_excel('example.xlsx',usecols=['wave','wind','current','X','Y','RZ'])
data = data.apply(lambda x: (x - np.mean(x)) / np.std(x))
n_cutoff = 200
X = np.array(data.loc[n_cutoff:,['wave','wind']])
Y = np.array(data.loc[n_cutoff:,['RZ']])
X = X.reshape(len(X),2)
X = np.append(X, [[0]*np.size(X, axis=1)], axis=0)
Y = Y.reshape(len(Y),1)
Y = np.insert(Y, 0, 0)
n_lag = 3
n_batch = 15
n = int(0.75*len(X))
generator = TimeseriesGenerator(X, Y, length=n_lag, batch_size=n_batch)
inputs = Input(shape=(n_lag,2))
hidden1 = LSTM(units=100,
activation='softmax',
recurrent_activation='linear',
dropout=0.5,
recurrent_dropout=0.5,
return_sequences=True)(inputs)
hidden2 = LSTM(units=30,
activation='softmax',
recurrent_activation='linear',
dropout=0.5,
recurrent_dropout=0.5,
return_sequences=False)(hidden1)
outputs = Dense(units=1,
activation='linear')(hidden2)
model = Model(inputs=inputs, outputs=outputs)
optimizer = Nadam(learning_rate=1e-2, beta_1=0.95, beta_2=0.9, epsilon=1e-7)
model.compile(loss='mean_squared_error', optimizer=optimizer)
history = model.fit(generator,
verbose=1,
steps_per_epoch=int(n/n_batch),
epochs=1,
shuffle=False,
callbacks=[EarlyStopping(monitor='loss', min_delta=0, patience=20, verbose=1, mode='auto'),
ReduceLROnPlateau(monitor='loss', factor=0.5, patience=10, verbose=1, mode='auto', cooldown=1),
TerminateOnNaN()])
Y_hat = model.predict(X[n:])
I am loading my pre-trained keras model and then trying to parallelize a large number of input data using dask? Unfortunately, I'm running into some issues with this relating to how I'm creating my dask array. Any guidance would be greatly appreciated!
Setup:
First I cloned from this repo https://github.com/sanchit2843/dlworkshop.git
Reproducible Code Example:
import numpy as np
import pandas as pd
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.pipeline import Pipeline, FeatureUnion
from sklearn.model_selection import train_test_split
from keras.models import load_model
import keras
from keras.models import Sequential
from keras.layers import Dense
from dask.distributed import Client
import warnings
import dask.array as DaskArray
warnings.filterwarnings('ignore')
dataset = pd.read_csv('data/train.csv')
X = dataset.drop(['price_range'], axis=1).values
y = dataset[['price_range']].values
# scale data
sc = StandardScaler()
X = sc.fit_transform(X)
ohe = OneHotEncoder()
y = ohe.fit_transform(y).toarray()
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size = 0.2)
# Neural network
model = Sequential()
model.add(Dense(16, input_dim=20, activation="relu"))
model.add(Dense(12, activation="relu"))
model.add(Dense(4, activation="softmax"))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
model.fit(X_train, y_train, epochs=100, batch_size=64)
# Use dask
client = Client()
def load_and_predict(input_data_chunk):
def contrastive_loss(y_true, y_pred):
margin = 1
square_pred = K.square(y_pred)
margin_square = K.square(K.maximum(margin - y_pred, 0))
return K.mean(y_true * square_pred + (1 - y_true) * margin_square)
mlflow.set_tracking_uri('<uri>')
mlflow.set_experiment('clean_parties_ml')
runs = mlflow.search_runs()
artifact_uri = runs.loc[runs['start_time'].idxmax()]['artifact_uri']
model = mlflow.keras.load_model(artifact_uri + '/model', custom_objects={'contrastive_loss': contrastive_loss})
y_pred = model.predict(input_data_chunk)
return y_pred
da_input_data = da.from_array(X_test, chunks=(100, None))
prediction_results = da_input_data.map_blocks(load_and_predict, dtype=X_test.dtype).compute()
The Error I'm receiving:
AttributeError: '_thread._local' object has no attribute 'value'
Keras/Tensorflow don't play nicely with other threaded systems. There is an ongoing issue on this topic here: https://github.com/dask/dask-examples/issues/35
I have a data set include with temperature, humidity and wind. Here I want to predict future temperature value in next hour.
I used LSTM to predict future temperature value.
But when I run the model it showed up this error Error when checking input: expected lstm_132_input to have 3 dimensions, but got array with shape (23, 1, 3, 1)
Can anyone help me to solve this problem?
Here is my code:
import datetime
import time
from sklearn.metrics import mean_squared_error
import matplotlib.pyplot as plt
from matplotlib.dates import DateFormatter
import numpy as np
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
from sklearn import preprocessing
from keras.layers.core import Dense, Dropout, Activation
from keras.activations import linear
from keras.layers.recurrent import LSTM
from keras.models import Sequential
from sklearn.preprocessing import MinMaxScaler
data = pd.read_csv('data6.csv' , sep=',')
data['date'] = pd.to_datetime(data['date'] + " " + data['time'], format='%m/%d/%Y %H:%M:%S')
data.set_index('time', inplace=True)
data = data.values
data = data.astype('float32')
# normalize the dataset
def create_data(train,X,n_out=1):
#data = np.reshape(train, (train.shape[0], train_shape[1], train_shape[2]))
x,y=list(),list()
start =0
for _ in range(len(data)):
in_end = start+X
out_end= in_end + n_out
if out_end < len(data):
x_input = data[start:in_end]
x.append(x_input)
y.append(data[in_end:out_end,0])
start +=1
return np.array(x),np.array(y)
scaler = MinMaxScaler()
data = scaler.fit_transform(data)
# split into train and test sets
train = int(len(data) * 0.6)
test = len(data) - train
train, test = data[0:train,:], data[train:len(data),:]
X=1
x_train, y_train = create_data(train,X)
x_test, y_test = create_data(test,X)
x_train=x_train.reshape(x_train.shape +(1,))
x_test=x_test.reshape(x_test.shape + (1,))
n_timesteps, n_features, n_outputs = x_train.shape[1], x_train.shape[2], x_train.shape[1]
model = Sequential()
model.add(LSTM(8, activation='relu', input_shape=(n_timesteps, n_features)))
model.add(Dense(8,activation='relu'))
model.add(Dense(n_outputs))
model.compile(loss='mse', optimizer='adam')
# fit network
model.fit(x_train,y_train, epochs=10,batch_size=1, verbose=0)
My csv file:
My csv file.
My error:
model summary :
you need to add activation to your last layer
model = Sequential()
model.add(LSTM(8, activation='relu', input_shape=(n_timesteps, n_features)))
model.add(Dense(8,activation='relu'))
# here
model.add(Dense(n_outputs,activation='relu'))
model.compile(loss='mse', optimizer='adam')
# fit network
model.fit(x_train,y_train, epochs=10,batch_size=1, verbose=0)
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)