Как я могу извлечь прогноз из вывода LSTM

Question

Я построил модель, используя LSTM для прогнозирования настроений. Модель выполнена с точностью более 80 процентов. Но когда я пытаюсь предсказать внешнюю ценность. model.predict () не предсказывает. Это просто обеспечивает настроение пустого массива.

Модель выглядит следующим образом.

import numpy as np
import pandas as pd

import warnings
warnings.filterwarnings("ignore")
from keras.utils import to_categorical
from keras.preprocessing.text import Tokenizer
from keras.preprocessing import sequence
import keras.backend as K
from keras.models import Sequential
from keras.layers import Dense,Embedding,LSTM
from sklearn.metrics import accuracy_score,confusion_matrix,classification_report


# Load Data
df = pd.read_csv('/content/drive/My Drive/Colab Notebooks/analysis.csv')
test = pd.read_csv('/content/drive/My Drive/Colab Notebooks/analysis.csv')
pd.set_option('display.max_colwidth', -1)

seed = 101 
np.random.seed(seed)

X = df['ride_review']
temp = test['ride_review']
y = to_categorical(df['sentiment'])
num_classes = df['sentiment'].nunique()

# Spilt Train Test sets
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,stratify=y,random_state=seed)
#print(X_train.shape, X_test.shape, y_train.shape, y_test.shape)

# Tokenize Text
max_features = 15000
tokenizer = Tokenizer(num_words=max_features)
tokenizer.fit_on_texts(list(X_train))
X_train = tokenizer.texts_to_sequences(X_train)
X_test = tokenizer.texts_to_sequences(X_test)
temp = tokenizer.texts_to_sequences(temp)

max_words = 50 
X_train = sequence.pad_sequences(X_train, maxlen=max_words)
X_test = sequence.pad_sequences(X_test, maxlen=max_words)
temp = sequence.pad_sequences(temp, maxlen=max_words)
#print(X_train.shape,X_test.shape)


batch_size = 128
epochs = 7
def get_model(max_features, embed_dim, embedding_matrix):
    np.random.seed(seed)
    K.clear_session()
    model = Sequential()
    model.add(Embedding(max_features, embed_dim, input_length=X_train.shape[1],
                       weights=[embedding_matrix]))#,trainable=False
    model.add(LSTM(100, dropout=0.2, recurrent_dropout=0.2))
    model.add(Dense(num_classes, activation='softmax'))
    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
    print(model.summary())
    return model

def get_coefs(word, *arr):
    return word, np.asarray(arr, dtype='float32')

def get_embed_mat(EMBEDDING_FILE, max_features=20000):
    # word vectors
    embeddings_index = dict(get_coefs(*o.rstrip().rsplit(' ')) for o in open(EMBEDDING_FILE, encoding='utf8'))
    print('Found %s word vectors.' % len(embeddings_index))

    # embedding matrix
    word_index = tokenizer.word_index
    num_words = min(max_features, len(word_index) + 1)
    all_embs = np.stack(embeddings_index.values()) #for random init
    embedding_matrix = np.random.normal(all_embs.mean(), all_embs.std(), 
                                        (num_words, embed_dim))
    for word, i in word_index.items():
        if i >= max_features:
            continue
        embedding_vector = embeddings_index.get(word)
        if embedding_vector is not None:
            embedding_matrix[i] = embedding_vector
    max_features = embedding_matrix.shape[0]

    return max_features, embedding_matrix

# embedding matrix
EMBEDDING_FILE = '/content/drive/My Drive/Colab Notebooks/Unwanted/glove.twitter.27B.200d.txt'
embed_dim = 100 #word vector dim
max_features, embedding_matrix = get_embed_mat(EMBEDDING_FILE)

# train the model
model = get_model(max_features, embed_dim, embedding_matrix)
model.fit(X_train, y_train, validation_data=(X_test, y_test),epochs=epochs, batch_size=batch_size, verbose=2)

sub = pd.read_csv('/content/drive/My Drive/Colab Notebooks/analysis.csv')
sub['Prediction Sentiment '] =  model.predict_classes(temp, batch_size=batch_size, verbose=0)
sub.to_csv("/content/drive/My Drive/Colab Notebooks/predict.csv", index=False)

Это код, который я использовал для прогнозирования внешнего значения:

a=['completed', 'running', 'new', 'york', 'marathon', 'requested', 'pool', 'ride', 'back', 'hotel']
from keras.preprocessing.text import Tokenizer
from keras.preprocessing.sequence import pad_sequences
tk = Tokenizer()
tk.fit_on_texts(a)
index_list = tk.texts_to_sequences(a)
a = pad_sequences(index_list, maxlen=50)
sentiment = model.predict(a)
print(sentiment)

Вывод выглядит следующим образом:

[[0.9001644  0.09983556]
 [0.8839435  0.11605652]
 [0.9005757  0.09942431]
 [0.9305595  0.06944045]
 [0.85847026 0.14152978]
 [0.8978375  0.10216247]
 [0.93535316 0.06464689]
 [0.9622155  0.03778455]
 [0.7891844  0.2108156 ]
 [0.9265106  0.07348941]]

Что это значит? Как я могу получить прогноз настроения?

Answer 1

Вам необходимо использовать dict для хранения ваших фактических меток:

act_labels = {val: ind for ind, val in enumerate(df['sentiment'].unique())}
df['sentiment'] = df['sentiment'].replace(act_labels)
y = to_categorical(df['sentiment'])

Чтобы получить прогнозы, вам необходимо сделать следующее:

rev_act_labels = {val: key for key, val in act_labels.items()}
predictions = np.argmax(sentiment, axis=1)
act_predictions  = [rev_act_labels[val] for val in predictions]
print(act_predictions)

, если model.predict_classes работает , то вы можете попробовать следующее:

rev_act_labels = {val: key for key, val in act_labels.items()}
sentiment = model.predict_classes(a)
# show the inputs and predicted outputs
for i in range(len(sentiment)):
    print("X=%s, Predicted=%s" % (a[i], rev_act_labels[sentiment[i])])