LSTM model using text data

Deep learning example code with text data




# Searching letters
df['column'][df['column'].str.contains('[^a-z ]')].sum()

# Replace letters
df['column'] = df['column'].str.replace('[^a-z ]','')

# delete sentence's head and tail's empty word
df['column'] = df['column'].str.strip()

# search duplicate data
df['column'].duplicated().sum()

# drop duplicate data
df.drop_duplicates(subset=['column'], inplace=True)

# Graph using value_counts()
df['column'].value_counts().plot(kind='bar')

# Split X and Y
features = df['column'].values
labels = df['column'].values

# TF-IDF
from sklearn.feature_extraction.text import TfidfVectorizer
tfidf = TfidfVectorizer()
x_train_v = tfidf.fit_transform(x_train)
x_test_v = tfidf.transform(x_test)

# Tokenizing
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
tokenizer = Tokenizer()
tokenizer.fit_on_texts(x_train)

# word:number mapping
tokenizer.index_word

# total word count
len(tokenizer.index_word)

# change sentence to array
x_train_seq = tokenizer.texts_to_sequences(x_train)
x_test_seq = tokenizer.texts_to_sequences(x_test)

# sentence's maximun lengh
max(len(line) for line in x_train_seq)

# Set all sentence length to maximun length
x_train_pad = pad_sequences(x_train_seq, maxlen=38)
x_test_pad = pad_sequences(x_test_seq, maxlen=38)

# HyperParameter
max_words = 47646 + 1    # add padding
max_len = 38~~ 
embedding_dim = 32~~

# model's first layer embedding 
model.add(Embedding(max_words, embedding_dim, input_length=max_len))
# LSTM layer (after 1st input layer)
model.add(LSTM(16, return_sequences=True))
model.add(LSTM(16, return_sequences=True))
model.add(Flatten())
model.add(Dense(128, activation='swish'))
model.add(Dense(32, activation='swish'))
model.add(Dense(6, activation='softmax'))

# Model Compile 
model.compile (loss = 'sparse_categorical_crossentropy',
              optimizer = 'adam',
              metrics = 'accuracy')
model.summary()

# EarlyStopping 
es = EarlyStopping(monitor='val_loss', patience=10, verbose=1)

# Set ModelCheckpoint
checkpoint_path = 'tmp_checkpoint.ckpt'
cp = ModelCheckpoint(checkpoint_path, monitor='val_loss', verbose=1, save_best_only=True)

# model fit
history = model.fit(x_train_pad, y_train, epochs=50, batch_size=512,
                      validation_split=0.2, verbose =1, callbacks=[es, cp])

# model evaluate using test dataset
model.evaluate(x_test_pad, y_test)

# Predict using model
predict = model.predict(x_test_pad[:1])

Comments

Post a Comment

Popular posts from this blog

[Kaggle] Titanic Survivor Classification

Titanic Survivor Classification Challenge From Kaggle. """ > - 0. Modules - 1. Train Data Load - 2. Null Data - 3. Outliers & One-Hot Encoding - 3.1. Outliers - 3.2. One-Hot-Encoding - 3.3. Merge DF - 4. Correlation Analysis - 4.1. Correlation Check (include dummies) - 4.2. Get Original Categorical Column Names - 4.3. Handle Categorical Columns Using Corr (del & dummy) - 5. Data Split-1 [Data and Label] - 6. Scaling - 7. Data Split-2 [Train and Validation] - 8. Test Data Load - 9. Machine Learning - 9.0. Comparison - 9.1. ML - Decision Tree Classifier - Grid Search - 9.2. ML - Random Forest Classifier - Grid Search - 9.3. ML - Logistic Regressor - Grid Search - 9.4. ML - XGBoost Classifier - Grid Search - 9.5. ML - LGBM Classifier - Grid Search - 9.6. ML - CatBoost Classifier - Grid Search - 10. Deep Learning - 10.1. Network Model - 10.2. Test Score - 11. Final Score Comparison - 12. Submit """ #============...
Read more

Machine Learning ShootOut

#=============== ======================================== import sklearn as sk import pandas as pd import numpy as np from sklearn.model_selection import train_test_split, GridSearchCV from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay from sklearn.metrics import accuracy_score, precision_score, recall_score, classification_report, f1_score, r2_score from sklearn.metrics import mean_absolute_error, mean_absolute_percentage_error, mean_squared_error, classification_report from sklearn.tree import DecisionTreeRegressor, DecisionTreeClassifier from sklearn.ensemble import RandomForestRegressor, RandomForestClassifier from sklearn.linear_model import LogisticRegression from xgboost.sklearn import XGBClassifier, XGBRegressor from lightgbm import LGBMRegressor, LGBMClassifier from catboost import CatBoostRegressor, CatBoostClassifier from sklearn.pipeline import make_pipeline #============================== ======================================== #===========...
Read more

[Kaggle] Pizza or Not Classification (Computer Vision)

Pizza or Not Binary Classification Challenge From Kaggle. """ > - 0. Modules - 1. Train Data Load - 1.1. Path and Check - 1.2. Amount Cnt - 1.3. Path & Files List - 1.4. Img Size Check - 2. Labeling - 2.1. Make Img & Label List - 2.2. Handling Img Ch Error - 3. Tensorization - 4. Data Split - 5. Test Data Load - 6. Learning - 6.1. Transfer - EfficientNet-B5 - 6.2. Transfer - ResNet50 V2 - 6.3. Transfer - Inception V3 - 6.4. CNN 7. Test Score 8. Submit """ #======================================== ======================================== import os from glob import glob import pathlib from PIL import Image import numpy as np import pandas as pd import matplotlib.pyplot as plt import tensorflow as tf from keras.models import Model, Sequential from keras.optimizers import Adam, Adamax, SGD, Nadam from sklearn.model_selection import train_test_split from keras.applications import EfficientNetB0, EfficientNetB4 from keras...
Read more