feature_engineering.py

# -*- coding: utf-8 -*-
"""
Created on Fri Apr 20 11:44:00 2018

@author: mgungor
"""
"""
#To import xgboost properly use the following code
dir = r'C:\Program Files\mingw-w64\x86_64-7.2.0-posix-seh-rt_v5-rev0\mingw64\bin'
import os 
os.environ['PATH'].count(dir)
os.environ['PATH'].find(dir)
os.environ['PATH'] = dir + ';' + os.environ['PATH']
"""
from sklearn.metrics import f1_score, accuracy_score
import pandas as pd
import numpy as np
import xgboost as xgb
from tqdm import tqdm
from sklearn.svm import SVC
from keras.models import Sequential
from keras.layers.recurrent import LSTM, GRU
from keras.layers.core import Dense, Activation, Dropout
from keras.layers.embeddings import Embedding
from keras.layers.normalization import BatchNormalization
from keras.utils import np_utils
from sklearn import preprocessing, decomposition, model_selection, metrics, pipeline
from sklearn.model_selection import GridSearchCV
from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
from sklearn.decomposition import TruncatedSVD
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import MultinomialNB
from keras.layers import GlobalMaxPooling1D, Conv1D, MaxPooling1D, Flatten, Bidirectional, SpatialDropout1D
from keras.preprocessing import sequence, text
from keras.callbacks import EarlyStopping
from nltk import word_tokenize
from nltk.corpus import stopwords
stop_words = stopwords.words('english')
#Read the training and testing data
train = pd.read_csv('train.csv')
test = pd.read_csv('test.csv')
#Read true labels for testing data
test_author = pd.read_csv("test_author.txt", header=None, names=["author"])

lbl_enc = preprocessing.LabelEncoder()
ytrain = lbl_enc.fit_transform(train.author.values)

# Always start with these features. They work (almost) everytime!
tfv = TfidfVectorizer(min_df=3,  max_features=None, 
            strip_accents='unicode', analyzer='word',token_pattern=r'\w{1,}',
            ngram_range=(1, 3), use_idf=1,smooth_idf=1,sublinear_tf=1,
            stop_words = 'english')

# Fitting TF-IDF to both training and test sets (semi-supervised learning)
xtrain = train.text.values
xvalid = test.text.values
yvalid = lbl_enc.fit_transform(test_author.author.values)
tfv.fit(list(xtrain) + list(xvalid))
xtrain_tfv =  tfv.transform(xtrain) 
xvalid_tfv = tfv.transform(xvalid)

clf = LogisticRegression(C=1.0)
clf.fit(xtrain_tfv, ytrain)
predictions = clf.predict(xvalid_tfv)

print("f1 Score")
print(f1_score(yvalid, predictions, average='macro'))

print("Accuracy")
print(accuracy_score(yvalid, predictions))

#Coun vectorizer
ctv = CountVectorizer(analyzer='word',token_pattern=r'\w{1,}',
            ngram_range=(1, 3), stop_words = 'english')

# Fitting Count Vectorizer to both training and test sets (semi-supervised learning)
ctv.fit(list(xtrain) + list(xvalid))
xtrain_ctv =  ctv.transform(xtrain) 
xvalid_ctv = ctv.transform(xvalid)

# Fitting a simple Logistic Regression on Counts
clf = LogisticRegression(C=1.0)
clf.fit(xtrain_ctv, ytrain)
predictions = clf.predict(xvalid_ctv)

print("f1 Score")
print(f1_score(yvalid, predictions, average='macro'))
print("f1 Score Individual")
print(f1_score(yvalid, predictions, average=None))
print("Accuracy")
print(accuracy_score(yvalid, predictions))

# Fitting a simple Naive Bayes on TFIDF
clf = MultinomialNB()
clf.fit(xtrain_tfv, ytrain)
predictions = clf.predict(xvalid_tfv)
print("f1 Score")
print(f1_score(yvalid, predictions, average='macro'))
print("f1 Score Individual")
print(f1_score(yvalid, predictions, average=None))
print("Accuracy")
print(accuracy_score(yvalid, predictions))
# Fitting a simple Naive Bayes on Counts
clf = MultinomialNB()
clf.fit(xtrain_ctv, ytrain)
predictions = clf.predict(xvalid_ctv)
print("f1 Score")
print(f1_score(yvalid, predictions, average='macro'))
print("f1 Score Individual")
print(f1_score(yvalid, predictions, average=None))
print("Accuracy")
print(accuracy_score(yvalid, predictions))

# Apply SVD, I chose 120 components. 120-200 components are good enough for SVM model.
svd = decomposition.TruncatedSVD(n_components=120)
svd.fit(xtrain_tfv)
xtrain_svd = svd.transform(xtrain_tfv)
xvalid_svd = svd.transform(xvalid_tfv)

# Scale the data obtained from SVD. Renaming variable to reuse without scaling.
scl = preprocessing.StandardScaler()
scl.fit(xtrain_svd)
xtrain_svd_scl = scl.transform(xtrain_svd)
xvalid_svd_scl = scl.transform(xvalid_svd)

# Fitting a simple SVM
clf = SVC(C=1.0)
clf.fit(xtrain_svd_scl, ytrain)
predictions = clf.predict(xvalid_svd_scl)
print("f1 Score")
print(f1_score(yvalid, predictions, average='macro'))
print("f1 Score Individual")
print(f1_score(yvalid, predictions, average=None))
print("Accuracy")
print(accuracy_score(yvalid, predictions))

# Apply SVD, I chose 120 components. 120-200 components are good enough for SVM model.
svd = decomposition.TruncatedSVD(n_components=200)
svd.fit(xtrain_tfv)
xtrain_svd = svd.transform(xtrain_tfv)
xvalid_svd = svd.transform(xvalid_tfv)

# Scale the data obtained from SVD. Renaming variable to reuse without scaling.
scl = preprocessing.StandardScaler()
scl.fit(xtrain_svd)
xtrain_svd_scl = scl.transform(xtrain_svd)
xvalid_svd_scl = scl.transform(xvalid_svd)

# Fitting a simple SVM
clf = SVC(C=1.0)
clf.fit(xtrain_svd_scl, ytrain)
predictions = clf.predict(xvalid_svd_scl)
print("f1 Score")
print(f1_score(yvalid, predictions, average='macro'))
print("f1 Score Individual")
print(f1_score(yvalid, predictions, average=None))
print("Accuracy")
print(accuracy_score(yvalid, predictions))

# Fitting a simple xgboost on tf-idf
clf = xgb.XGBClassifier(max_depth=7, n_estimators=200, colsample_bytree=0.8, 
                        subsample=0.8, nthread=10, learning_rate=0.1)
clf.fit(xtrain_tfv.tocsc(), ytrain)
predictions = clf.predict(xvalid_tfv.tocsc())
print("f1 Score")
print(f1_score(yvalid, predictions, average='macro'))
print("f1 Score Individual")
print(f1_score(yvalid, predictions, average=None))
print("Accuracy")
print(accuracy_score(yvalid, predictions))

# Fitting a simple xgboost on counvectorizer
clf = xgb.XGBClassifier(max_depth=7, n_estimators=200, colsample_bytree=0.8, 
                        subsample=0.8, nthread=10, learning_rate=0.1)
clf.fit(xtrain_ctv.tocsc(), ytrain)
predictions = clf.predict(xvalid_ctv.tocsc())
print("f1 Score")
print(f1_score(yvalid, predictions, average='macro'))
print("f1 Score Individual")
print(f1_score(yvalid, predictions, average=None))
print("Accuracy")
print(accuracy_score(yvalid, predictions))

# Fitting a simple xgboost on tf-idf svd features
clf = xgb.XGBClassifier(max_depth=7, n_estimators=200, colsample_bytree=0.8, 
                        subsample=0.8, nthread=10, learning_rate=0.1)
clf.fit(xtrain_svd, ytrain)
predictions = clf.predict(xvalid_svd)
print("f1 Score")
print(f1_score(yvalid, predictions, average='macro'))
print("f1 Score Individual")
print(f1_score(yvalid, predictions, average=None))
print("Accuracy")
print(accuracy_score(yvalid, predictions))

#Work on Word2vec

embeddings_index = {}
f = open('glove.840B.300d.txt',encoding="utf8")
for line in tqdm(f):
    values = line.split()
    word = "".join(values[0:len(values)-300])
    coefs = np.asarray(values[len(values)-300:len(values)], dtype='float32')
    embeddings_index[word] = coefs
f.close()

# this function creates a normalized vector for the whole sentence
def sent2vec(s):
    words = str(s).lower()
    words = word_tokenize(words)
    words = [w for w in words if not w in stop_words]
    words = [w for w in words if w.isalpha()]
    M = []
    for w in words:
        try:
            M.append(embeddings_index[w])
        except:
            continue
    M = np.array(M)
    v = M.sum(axis=0)
    if type(v) != np.ndarray:
        return np.zeros(300)
    return v / np.sqrt((v ** 2).sum())

xtrain_glove = [sent2vec(x) for x in tqdm(xtrain)]
xvalid_glove = [sent2vec(x) for x in tqdm(xvalid)]

xtrain_glove = np.array(xtrain_glove)
xvalid_glove = np.array(xvalid_glove)

# Fitting a simple xgboost on glove features
clf = xgb.XGBClassifier(nthread=10, silent=False)
clf.fit(xtrain_glove, ytrain)
predictions = clf.predict(xvalid_glove)
print("f1 Score")
print(f1_score(yvalid, predictions, average='macro'))
print("f1 Score Individual")
print(f1_score(yvalid, predictions, average=None))
print("Accuracy")
print(accuracy_score(yvalid, predictions))
# Fitting a simple xgboost on glove features
clf = xgb.XGBClassifier(max_depth=7, n_estimators=200, colsample_bytree=0.8, 
                        subsample=0.8, nthread=10, learning_rate=0.1, silent=False)
clf.fit(xtrain_glove, ytrain)
predictions = clf.predict(xvalid_glove)
print("f1 Score")
print(f1_score(yvalid, predictions, average='macro'))
print("f1 Score Individual")
print(f1_score(yvalid, predictions, average=None))
print("Accuracy")
print(accuracy_score(yvalid, predictions))
# Fitting a simple SVM on Sentence Vectors
clf = SVC(C=1.0)
clf.fit(xtrain_glove, ytrain)
predictions = clf.predict(xvalid_glove)
print("f1 Score")
print(f1_score(yvalid, predictions, average='macro'))
print("f1 Score Individual")
print(f1_score(yvalid, predictions, average=None))
print("Accuracy")
print(accuracy_score(yvalid, predictions))
# Fitting a simple Logistic Regression on Sentence Vectors
clf = LogisticRegression(C=1.0)
clf.fit(xtrain_glove, ytrain)
predictions = clf.predict(xvalid_glove)
print("f1 Score")
print(f1_score(yvalid, predictions, average='macro'))
print("f1 Score Individual")
print(f1_score(yvalid, predictions, average=None))
print("Accuracy")
print(accuracy_score(yvalid, predictions))

###############################################################################
# scale the data before any neural net:
scl = preprocessing.StandardScaler()
xtrain_glove_scl = scl.fit_transform(xtrain_glove)
xvalid_glove_scl = scl.transform(xvalid_glove)

# we need to binarize the labels for the neural net
ytrain_enc = np_utils.to_categorical(ytrain)
yvalid_enc = np_utils.to_categorical(yvalid)

# create a simple 3 layer sequential neural net
model = Sequential()

model.add(Dense(300, input_dim=300, activation='relu'))
model.add(Dropout(0.2))
model.add(BatchNormalization())

model.add(Dense(300, activation='relu'))
model.add(Dropout(0.3))
model.add(BatchNormalization())

model.add(Dense(3))
model.add(Activation('softmax'))

# compile the model
import tensorflow as tf


def f1_score(y_true, y_pred):
    y_true = tf.cast(y_true, "int32")
    y_pred = tf.cast(tf.round(y_pred), "int32") # implicit 0.5 threshold via tf.round
    y_correct = y_true * y_pred
    sum_true = tf.reduce_sum(y_true, axis=1)
    sum_pred = tf.reduce_sum(y_pred, axis=1)
    sum_correct = tf.reduce_sum(y_correct, axis=1)
    precision = sum_correct / sum_pred
    recall = sum_correct / sum_true
    f_score = 2 * precision * recall / (precision + recall)
    f_score = tf.where(tf.is_nan(f_score), tf.zeros_like(f_score), f_score)
    return tf.reduce_mean(f_score)
model.compile(loss='binary_crossentropy', optimizer='adam',metrics=[f1_score])

model.fit(xtrain_glove_scl, y=ytrain_enc, batch_size=64, 
          epochs=5, verbose=1, 
          validation_data=(xvalid_glove_scl, yvalid_enc))

#Implement LSTM now
# using keras tokenizer here
token = text.Tokenizer(num_words=None)
max_len = 70

token.fit_on_texts(list(xtrain) + list(xvalid))
xtrain_seq = token.texts_to_sequences(xtrain)
xvalid_seq = token.texts_to_sequences(xvalid)

# zero pad the sequences
xtrain_pad = sequence.pad_sequences(xtrain_seq, maxlen=max_len)
xvalid_pad = sequence.pad_sequences(xvalid_seq, maxlen=max_len)

word_index = token.word_index

# create an embedding matrix for the words we have in the dataset
embedding_matrix = np.zeros((len(word_index) + 1, 300))
for word, i in tqdm(word_index.items()):
    embedding_vector = embeddings_index.get(word)
    if embedding_vector is not None:
        embedding_matrix[i] = embedding_vector
        
# A simple LSTM with glove embeddings and two dense layers
model = Sequential()
model.add(Embedding(len(word_index) + 1,
                     300,
                     weights=[embedding_matrix],
                     input_length=max_len,
                     trainable=False))
model.add(SpatialDropout1D(0.3))
model.add(LSTM(100, dropout=0.3, recurrent_dropout=0.3))

model.add(Dense(1024, activation='relu'))
model.add(Dropout(0.8))

model.add(Dense(1024, activation='relu'))
model.add(Dropout(0.8))

model.add(Dense(3))
model.add(Activation('softmax'))
model.compile(loss='binary_crossentropy', optimizer='adam',metrics=[f1_score])
# Fit the model with early stopping callback
earlystop = EarlyStopping(monitor='val_loss', min_delta=0, patience=3, verbose=0, mode='auto')
model.fit(xtrain_pad, y=ytrain_enc, batch_size=512, epochs=100, 
          verbose=1, validation_data=(xvalid_pad, yvalid_enc), callbacks=[earlystop])

# A simple bidirectional LSTM with glove embeddings and two dense layers
model = Sequential()
model.add(Embedding(len(word_index) + 1,
                     300,
                     weights=[embedding_matrix],
                     input_length=max_len,
                     trainable=False))
model.add(SpatialDropout1D(0.3))
model.add(Bidirectional(LSTM(300, dropout=0.3, recurrent_dropout=0.3)))

model.add(Dense(1024, activation='relu'))
model.add(Dropout(0.8))

model.add(Dense(1024, activation='relu'))
model.add(Dropout(0.8))

model.add(Dense(3))
model.add(Activation('softmax'))
model.compile(loss='binary_crossentropy', optimizer='adam',metrics=[f1_score])

# Fit the model with early stopping callback
earlystop = EarlyStopping(monitor='val_loss', min_delta=0, patience=3, verbose=0, mode='auto')
model.fit(xtrain_pad, y=ytrain_enc, batch_size=512, epochs=100, 
          verbose=1, validation_data=(xvalid_pad, yvalid_enc), callbacks=[earlystop])

# GRU with glove embeddings and two dense layers
model = Sequential()
model.add(Embedding(len(word_index) + 1,
                     300,
                     weights=[embedding_matrix],
                     input_length=max_len,
                     trainable=False))
model.add(SpatialDropout1D(0.3))
model.add(GRU(300, dropout=0.3, recurrent_dropout=0.3, return_sequences=True))
model.add(GRU(300, dropout=0.3, recurrent_dropout=0.3))

model.add(Dense(1024, activation='relu'))
model.add(Dropout(0.8))

model.add(Dense(1024, activation='relu'))
model.add(Dropout(0.8))

model.add(Dense(3))
model.add(Activation('softmax'))
model.compile(loss='binary_crossentropy', optimizer='adam',metrics=[f1_score])

# Fit the model with early stopping callback
earlystop = EarlyStopping(monitor='val_loss', min_delta=0, patience=3, verbose=0, mode='auto')
model.fit(xtrain_pad, y=ytrain_enc, batch_size=512, epochs=100, 
          verbose=1, validation_data=(xvalid_pad, yvalid_enc), callbacks=[earlystop])


# this is the main ensembling class. how to use it is in the next cell!
import numpy as np
from sklearn.metrics import roc_auc_score
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import StratifiedKFold, KFold
import pandas as pd
import os
import sys
import logging

logging.basicConfig(
    level=logging.DEBUG,
    format="[%(asctime)s] %(levelname)s %(message)s",
    datefmt="%H:%M:%S", stream=sys.stdout)
logger = logging.getLogger(__name__)


class Ensembler(object):
    def __init__(self, model_dict, num_folds=3, task_type='classification', optimize=roc_auc_score,
                 lower_is_better=False, save_path=None):
        """
        Ensembler init function
        :param model_dict: model dictionary, see README for its format
        :param num_folds: the number of folds for ensembling
        :param task_type: classification or regression
        :param optimize: the function to optimize for, e.g. AUC, logloss, etc. Must have two arguments y_test and y_pred
        :param lower_is_better: is lower value of optimization function better or higher
        :param save_path: path to which model pickles will be dumped to along with generated predictions, or None
        """

        self.model_dict = model_dict
        self.levels = len(self.model_dict)
        self.num_folds = num_folds
        self.task_type = task_type
        self.optimize = optimize
        self.lower_is_better = lower_is_better
        self.save_path = save_path

        self.training_data = None
        self.test_data = None
        self.y = None
        self.lbl_enc = None
        self.y_enc = None
        self.train_prediction_dict = None
        self.test_prediction_dict = None
        self.num_classes = None

    def fit(self, training_data, y, lentrain):
        """
        :param training_data: training data in tabular format
        :param y: binary, multi-class or regression
        :return: chain of models to be used in prediction
        """

        self.training_data = training_data
        self.y = y

        if self.task_type == 'classification':
            self.num_classes = len(np.unique(self.y))
            logger.info("Found %d classes", self.num_classes)
            self.lbl_enc = LabelEncoder()
            self.y_enc = self.lbl_enc.fit_transform(self.y)
            kf = StratifiedKFold(n_splits=self.num_folds)
            train_prediction_shape = (lentrain, self.num_classes)
        else:
            self.num_classes = -1
            self.y_enc = self.y
            kf = KFold(n_splits=self.num_folds)
            train_prediction_shape = (lentrain, 1)

        self.train_prediction_dict = {}
        for level in range(self.levels):
            self.train_prediction_dict[level] = np.zeros((train_prediction_shape[0],
                                                          train_prediction_shape[1] * len(self.model_dict[level])))

        for level in range(self.levels):

            if level == 0:
                temp_train = self.training_data
            else:
                temp_train = self.train_prediction_dict[level - 1]

            for model_num, model in enumerate(self.model_dict[level]):
                validation_scores = []
                foldnum = 1
                for train_index, valid_index in kf.split(self.train_prediction_dict[0], self.y_enc):
                    logger.info("Training Level %d Fold # %d. Model # %d", level, foldnum, model_num)

                    if level != 0:
                        l_training_data = temp_train[train_index]
                        l_validation_data = temp_train[valid_index]
                        model.fit(l_training_data, self.y_enc[train_index])
                    else:
                        l0_training_data = temp_train[0][model_num]
                        if type(l0_training_data) == list:
                            l_training_data = [x[train_index] for x in l0_training_data]
                            l_validation_data = [x[valid_index] for x in l0_training_data]
                        else:
                            l_training_data = l0_training_data[train_index]
                            l_validation_data = l0_training_data[valid_index]
                        model.fit(l_training_data, self.y_enc[train_index])

                    logger.info("Predicting Level %d. Fold # %d. Model # %d", level, foldnum, model_num)

                    if self.task_type == 'classification':
                        temp_train_predictions = model.predict_proba(l_validation_data)
                        self.train_prediction_dict[level][valid_index,
                        (model_num * self.num_classes):(model_num * self.num_classes) +
                                                       self.num_classes] = temp_train_predictions

                    else:
                        temp_train_predictions = model.predict(l_validation_data)
                        self.train_prediction_dict[level][valid_index, model_num] = temp_train_predictions
                    validation_score = self.optimize(self.y_enc[valid_index], temp_train_predictions)
                    validation_scores.append(validation_score)
                    logger.info("Level %d. Fold # %d. Model # %d. Validation Score = %f", level, foldnum, model_num,
                                validation_score)
                    foldnum += 1
                avg_score = np.mean(validation_scores)
                std_score = np.std(validation_scores)
                logger.info("Level %d. Model # %d. Mean Score = %f. Std Dev = %f", level, model_num,
                            avg_score, std_score)

            logger.info("Saving predictions for level # %d", level)
            train_predictions_df = pd.DataFrame(self.train_prediction_dict[level])
            train_predictions_df.to_csv(os.path.join(self.save_path, "train_predictions_level_" + str(level) + ".csv"),
                                        index=False, header=None)

        return self.train_prediction_dict

    def predict(self, test_data, lentest):
        self.test_data = test_data
        if self.task_type == 'classification':
            test_prediction_shape = (lentest, self.num_classes)
        else:
            test_prediction_shape = (lentest, 1)

        self.test_prediction_dict = {}
        for level in range(self.levels):
            self.test_prediction_dict[level] = np.zeros((test_prediction_shape[0],
                                                         test_prediction_shape[1] * len(self.model_dict[level])))
        self.test_data = test_data
        for level in range(self.levels):
            if level == 0:
                temp_train = self.training_data
                temp_test = self.test_data
            else:
                temp_train = self.train_prediction_dict[level - 1]
                temp_test = self.test_prediction_dict[level - 1]

            for model_num, model in enumerate(self.model_dict[level]):

                logger.info("Training Fulldata Level %d. Model # %d", level, model_num)
                if level == 0:
                    model.fit(temp_train[0][model_num], self.y_enc)
                else:
                    model.fit(temp_train, self.y_enc)

                logger.info("Predicting Test Level %d. Model # %d", level, model_num)

                if self.task_type == 'classification':
                    if level == 0:
                        temp_test_predictions = model.predict_proba(temp_test[0][model_num])
                    else:
                        temp_test_predictions = model.predict_proba(temp_test)
                    self.test_prediction_dict[level][:, (model_num * self.num_classes): (model_num * self.num_classes) +
                                                                                        self.num_classes] = temp_test_predictions

                else:
                    if level == 0:
                        temp_test_predictions = model.predict(temp_test[0][model_num])
                    else:
                        temp_test_predictions = model.predict(temp_test)
                    self.test_prediction_dict[level][:, model_num] = temp_test_predictions

            test_predictions_df = pd.DataFrame(self.test_prediction_dict[level])
            test_predictions_df.to_csv(os.path.join(self.save_path, "test_predictions_level_" + str(level) + ".csv"),
                                       index=False, header=None)

        return self.test_prediction_dict
    
# specify the data to be used for every level of ensembling:
train_data_dict = {0: [xtrain_tfv, xtrain_ctv, xtrain_tfv, xtrain_ctv], 1: [xtrain_glove]}
test_data_dict = {0: [xvalid_tfv, xvalid_ctv, xvalid_tfv, xvalid_ctv], 1: [xvalid_glove]}

model_dict = {0: [LogisticRegression(), LogisticRegression(), MultinomialNB(alpha=0.1), MultinomialNB()],

              1: [xgb.XGBClassifier(silent=True, n_estimators=120, max_depth=7)]}

def multiclass_logloss(actual, predicted, eps=1e-15):
    """Multi class version of Logarithmic Loss metric.
    :param actual: Array containing the actual target classes
    :param predicted: Matrix with class predictions, one probability per class
    """
    # Convert 'actual' to a binary array if it's not already:
    if len(actual.shape) == 1:
        actual2 = np.zeros((actual.shape[0], predicted.shape[1]))
        for i, val in enumerate(actual):
            actual2[i, val] = 1
        actual = actual2

    clip = np.clip(predicted, eps, 1 - eps)
    rows = actual.shape[0]
    vsota = np.sum(actual * np.log(clip))
    return -1.0 / rows * vsota

ens = Ensembler(model_dict=model_dict, num_folds=3, task_type='classification',
                optimize=multiclass_logloss, lower_is_better=True, save_path='')

ens.fit(train_data_dict, ytrain, lentrain=xtrain_glove.shape[0])
preds = ens.predict(test_data_dict, lentest=xvalid_glove.shape[0])

# Create a session
sess = tf.InteractiveSession()


# Index of top values
indexes = tf.argmax(preds[1], axis=1)
predictions = indexes.eval()
print("f1 Score")
print(f1_score(yvalid, predictions, average='macro'))
print("f1 Score Individual")
print(f1_score(yvalid, predictions, average=None))
print("Accuracy")
print(accuracy_score(yvalid, predictions)) 

#Save mat file
import scipy.io

scipy.io.savemat('xtrain_glove.mat', mdict={'xtrain_glove': xtrain_glove})
scipy.io.savemat('xvalid_glove.mat', mdict={'xvalid_glove': xvalid_glove})
scipy.io.savemat('yvalid.mat', mdict={'yvalid': yvalid})
scipy.io.savemat('ytrain.mat', mdict={'ytrain': ytrain})