NLP Approaching (Almost) Any NLP Problem on Kaggle2탄

라이브 러리 임포트

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')

 

데이터 받기

train = pd.read_csv('../input/spooky/train.csv')
test = pd.read_csv('../input/spooky/test.csv')
sample = pd.read_csv('../input/spooky/sample_submission.csv')

성능 예측 하기

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

텍스트 데이터를 정수형데이터로 변환하기

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

데이터 나누기

xtrain, xvalid, ytrain, yvalid = train_test_split(train.text.values, y, 
                                                  stratify=y, 
                                                  random_state=42, 
                                                  test_size=0.1, shuffle=True)

tf-idf 적용

# 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)
tfv.fit(list(xtrain) + list(xvalid))
xtrain_tfv =  tfv.transform(xtrain) 
xvalid_tfv = tfv.transform(xvalid)

로직스틱 회귀알고리즘 적용

# Fitting a simple Logistic Regression on TFIDF
clf = LogisticRegression(C=1.0)
clf.fit(xtrain_tfv, ytrain)
predictions = clf.predict_proba(xvalid_tfv)

print ("logloss: %0.3f " % multiclass_logloss(yvalid, predictions))

 

카운터 벡터라이저 사용

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)

로지스틱 회귀 사용

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

print ("logloss: %0.3f " % multiclass_logloss(yvalid, predictions))

나이즈 베이사용

# Fitting a simple Naive Bayes on TFIDF
clf = MultinomialNB()
clf.fit(xtrain_tfv, ytrain)
predictions = clf.predict_proba(xvalid_tfv)

print ("logloss: %0.3f " % multiclass_logloss(yvalid, predictions))

svd알고리즘을 주성분 120으로 축소하는 객체생성

# 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)

예측하기

# Fitting a simple SVM
clf = SVC(C=1.0, probability=True) # since we need probabilities
clf.fit(xtrain_svd_scl, ytrain)
predictions = clf.predict_proba(xvalid_svd_scl)

print ("logloss: %0.3f " % multiclass_logloss(yvalid, predictions))

xgboosting 예측

# 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_proba(xvalid_tfv.tocsc())

print ("logloss: %0.3f " % multiclass_logloss(yvalid, predictions))