自然语言处理实例

自然语言处理实例

数据简介: Disasters on social media

社交媒体上有些讨论是关于灾难，疾病，暴乱的，有些只是开玩笑或者是电影情节，我们该如何让机器能分辨出这两种讨论呢？

import keras
import nltk
import pandas as pd
import numpy as np
import re
import codecs

  

 

  
1
  
2
  
3
  
4
  
5
  
6
 

questions = pd.read_csv("socialmedia_relevant_cols_clean.csv")
questions.columns=['text', 'choose_one', 'class_label']
questions.head()

  

 

  
1
  
2
  
3
 

questions.describe()

  

 

  
1
 

数据清洗，去掉无用字符

def standardize_text(df, text_field): df[text_field] = df[text_field].str.replace(r"http\S+", "") df[text_field] = df[text_field].str.replace(r"http", "") df[text_field] = df[text_field].str.replace(r"@\S+", "") df[text_field] = df[text_field].str.replace(r"[^A-Za-z0-9(),!?@\'\`\"\_\n]", " ") df[text_field] = df[text_field].str.replace(r"@", "at") df[text_field] = df[text_field].str.lower() return df

questions = standardize_text(questions, "text")

questions.to_csv("clean_data.csv")
questions.head()

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
  
10
  
11
  
12
  
13
 

clean_questions = pd.read_csv("clean_data.csv")
clean_questions.tail()

  

 

  
1
  
2
 

数据分布情况

数据是否倾斜

clean_questions.groupby("class_label").count()

  

 

  
1
 

看起来还算均衡的

处理流程

• 分词
• 训练与测试集
• 检查与验证

from nltk.tokenize import RegexpTokenizer

tokenizer = RegexpTokenizer(r'\w+')

clean_questions["tokens"] = clean_questions["text"].apply(tokenizer.tokenize)
clean_questions.head()

  

 

  
1
  
2
  
3
  
4
  
5
  
6
 

语料库情况

from keras.preprocessing.text import Tokenizer
from keras.preprocessing.sequence import pad_sequences
from keras.utils import to_categorical

all_words = [word for tokens in clean_questions["tokens"] for word in tokens]
sentence_lengths = [len(tokens) for tokens in clean_questions["tokens"]]
VOCAB = sorted(list(set(all_words)))
print("%s words total, with a vocabulary size of %s" % (len(all_words), len(VOCAB)))
print("Max sentence length is %s" % max(sentence_lengths))

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
 

154724 words total, with a vocabulary size of 18101
Max sentence length is 34

  

 

  
1
  
2
 

句子长度情况

import matplotlib.pyplot as plt

fig = plt.figure(figsize=(10, 10)) 
plt.xlabel('Sentence length')
plt.ylabel('Number of sentences')
plt.hist(sentence_lengths)
plt.show()

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
 

特征如何构建？

Bag of Words Counts

from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer

def cv(data): count_vectorizer = CountVectorizer() emb = count_vectorizer.fit_transform(data) return emb, count_vectorizer

list_corpus = clean_questions["text"].tolist()
list_labels = clean_questions["class_label"].tolist()

X_train, X_test, y_train, y_test = train_test_split(list_corpus, list_labels, test_size=0.2, random_state=40)

X_train_counts, count_vectorizer = cv(X_train)
X_test_counts = count_vectorizer.transform(X_test)

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
  
10
  
11
  
12
  
13
  
14
  
15
  
16
  
17
  
18
 

PCA展示Bag of Words

from sklearn.decomposition import PCA, TruncatedSVD
import matplotlib
import matplotlib.patches as mpatches


def plot_LSA(test_data, test_labels, savepath="PCA_demo.csv", plot=True): lsa = TruncatedSVD(n_components=2) lsa.fit(test_data) lsa_scores = lsa.transform(test_data) color_mapper = {label:idx for idx,label in enumerate(set(test_labels))} color_column = [color_mapper[label] for label in test_labels] colors = ['orange','blue','blue'] if plot: plt.scatter(lsa_scores[:,0], lsa_scores[:,1], s=8, alpha=.8, c=test_labels, cmap=matplotlib.colors.ListedColormap(colors)) red_patch = mpatches.Patch(color='orange', label='Irrelevant') green_patch = mpatches.Patch(color='blue', label='Disaster') plt.legend(handles=[red_patch, green_patch], prop={'size': 30})


fig = plt.figure(figsize=(16, 16)) plot_LSA(X_train_counts, y_train)
plt.show()

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
  
10
  
11
  
12
  
13
  
14
  
15
  
16
  
17
  
18
  
19
  
20
  
21
  
22
 

看起来并没有将这两类点区分开

逻辑回归看一下结果

from sklearn.linear_model import LogisticRegression

clf = LogisticRegression(C=30.0, class_weight='balanced', solver='newton-cg', multi_class='multinomial', n_jobs=-1, random_state=40)
clf.fit(X_train_counts, y_train)

y_predicted_counts = clf.predict(X_test_counts)

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
 

评估

from sklearn.metrics import accuracy_score, f1_score, precision_score, recall_score, classification_report

def get_metrics(y_test, y_predicted): # true positives / (true positives+false positives) precision = precision_score(y_test, y_predicted, pos_label=None, average='weighted') # true positives / (true positives + false negatives) recall = recall_score(y_test, y_predicted, pos_label=None, average='weighted') # harmonic mean of precision and recall f1 = f1_score(y_test, y_predicted, pos_label=None, average='weighted') # true positives + true negatives/ total accuracy = accuracy_score(y_test, y_predicted) return accuracy, precision, recall, f1

accuracy, precision, recall, f1 = get_metrics(y_test, y_predicted_counts)
print("accuracy = %.3f, precision = %.3f, recall = %.3f, f1 = %.3f" % (accuracy, precision, recall, f1))

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
  
10
  
11
  
12
  
13
  
14
  
15
  
16
  
17
  
18
  
19
 

accuracy = 0.754, precision = 0.752, recall = 0.754, f1 = 0.753

  

 

  
1
 

混淆矩阵检查

import numpy as np
import itertools
from sklearn.metrics import confusion_matrix

def plot_confusion_matrix(cm, classes, normalize=False, title='Confusion matrix', cmap=plt.cm.winter): if normalize: cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis] plt.imshow(cm, interpolation='nearest', cmap=cmap) plt.title(title, fontsize=30) plt.colorbar() tick_marks = np.arange(len(classes)) plt.xticks(tick_marks, classes, fontsize=20) plt.yticks(tick_marks, classes, fontsize=20) fmt = '.2f' if normalize else 'd' thresh = cm.max() / 2. for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])): plt.text(j, i, format(cm[i, j], fmt), horizontalalignment="center", color="white" if cm[i, j] < thresh else "black", fontsize=40) plt.tight_layout() plt.ylabel('True label', fontsize=30) plt.xlabel('Predicted label', fontsize=30) return plt

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
  
10
  
11
  
12
  
13
  
14
  
15
  
16
  
17
  
18
  
19
  
20
  
21
  
22
  
23
  
24
  
25
  
26
  
27
  
28
  
29
 

cm = confusion_matrix(y_test, y_predicted_counts)
fig = plt.figure(figsize=(10, 10))
plot = plot_confusion_matrix(cm, classes=['Irrelevant','Disaster','Unsure'], normalize=False, title='Confusion matrix')
plt.show()
print(cm)

  

 

  
1
  
2
  
3
  
4
  
5
 

[[970 251   3]
 [274 670   1]
 [  3   4   0]]

  

 

  
1
  
2
  
3
 

第三类咋没有一个呢。。。因为数据里面就没几个啊。。。

进一步检查模型的关注点

def get_most_important_features(vectorizer, model, n=5): index_to_word = {v:k for k,v in vectorizer.vocabulary_.items()} # loop for each class classes ={} for class_index in range(model.coef_.shape[0]): word_importances = [(el, index_to_word[i]) for i,el in enumerate(model.coef_[class_index])] sorted_coeff = sorted(word_importances, key = lambda x : x[0], reverse=True) tops = sorted(sorted_coeff[:n], key = lambda x : x[0]) bottom = sorted_coeff[-n:] classes[class_index] = { 'tops':tops, 'bottom':bottom } return classes

importance = get_most_important_features(count_vectorizer, clf, 10)

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
  
10
  
11
  
12
  
13
  
14
  
15
  
16
  
17
 

def plot_important_words(top_scores, top_words, bottom_scores, bottom_words, name): y_pos = np.arange(len(top_words)) top_pairs = [(a,b) for a,b in zip(top_words, top_scores)] top_pairs = sorted(top_pairs, key=lambda x: x[1]) bottom_pairs = [(a,b) for a,b in zip(bottom_words, bottom_scores)] bottom_pairs = sorted(bottom_pairs, key=lambda x: x[1], reverse=True) top_words = [a[0] for a in top_pairs] top_scores = [a[1] for a in top_pairs] bottom_words = [a[0] for a in bottom_pairs] bottom_scores = [a[1] for a in bottom_pairs] fig = plt.figure(figsize=(10, 10)) plt.subplot(121) plt.barh(y_pos,bottom_scores, align='center', alpha=0.5) plt.title('Irrelevant', fontsize=20) plt.yticks(y_pos, bottom_words, fontsize=14) plt.suptitle('Key words', fontsize=16) plt.xlabel('Importance', fontsize=20) plt.subplot(122) plt.barh(y_pos,top_scores, align='center', alpha=0.5) plt.title('Disaster', fontsize=20) plt.yticks(y_pos, top_words, fontsize=14) plt.suptitle(name, fontsize=16) plt.xlabel('Importance', fontsize=20) plt.subplots_adjust(wspace=0.8) plt.show()

top_scores = [a[0] for a in importance[1]['tops']]
top_words = [a[1] for a in importance[1]['tops']]
bottom_scores = [a[0] for a in importance[1]['bottom']]
bottom_words = [a[1] for a in importance[1]['bottom']]

plot_important_words(top_scores, top_words, bottom_scores, bottom_words, "Most important words for relevance")

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
  
10
  
11
  
12
  
13
  
14
  
15
  
16
  
17
  
18
  
19
  
20
  
21
  
22
  
23
  
24
  
25
  
26
  
27
  
28
  
29
  
30
  
31
  
32
  
33
  
34
  
35
  
36
  
37
  
38
  
39
 

我们的模型找到了一些模式，但是看起来还不够好

TFIDF Bag of Words

这样我们就不均等对待每一个词了

def tfidf(data): tfidf_vectorizer = TfidfVectorizer() train = tfidf_vectorizer.fit_transform(data) return train, tfidf_vectorizer

X_train_tfidf, tfidf_vectorizer = tfidf(X_train)
X_test_tfidf = tfidf_vectorizer.transform(X_test)

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
  
9
 

F:\anaconda\lib\site-packages\sklearn\feature_extraction\text.py:1089: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
  if hasattr(X, 'dtype') and np.issubdtype(X.dtype, np.float):

  

 

  
1
  
2
 

fig = plt.figure(figsize=(16, 16)) plot_LSA(X_train_tfidf, y_train)
plt.show()

  

 

  
1
  
2
  
3
 

看起来好那么一丁丁丁丁点

clf_tfidf = LogisticRegression(C=30.0, class_weight='balanced', solver='newton-cg', multi_class='multinomial', n_jobs=-1, random_state=40)
clf_tfidf.fit(X_train_tfidf, y_train)

y_predicted_tfidf = clf_tfidf.predict(X_test_tfidf)

  

 

  
1
  
2
  
3
  
4
  
5
 

accuracy_tfidf, precision_tfidf, recall_tfidf, f1_tfidf = get_metrics(y_test, y_predicted_tfidf)
print("accuracy = %.3f, precision = %.3f, recall = %.3f, f1 = %.3f" % (accuracy_tfidf, precision_tfidf, recall_tfidf, f1_tfidf))

  

 

  
1
  
2
  
3
 

accuracy = 0.762, precision = 0.760, recall = 0.762, f1 = 0.761

  

 

  
1
 

cm2 = confusion_matrix(y_test, y_predicted_tfidf)
fig = plt.figure(figsize=(10, 10))
plot = plot_confusion_matrix(cm2, classes=['Irrelevant','Disaster','Unsure'], normalize=False, title='Confusion matrix')
plt.show()
print("TFIDF confusion matrix")
print(cm2)
print("BoW confusion matrix")
print(cm)

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
 

TFIDF confusion matrix
[[974 249   1]
 [261 684   0]
 [  3   4   0]]
BoW confusion matrix
[[970 251   3]
 [274 670   1]
 [  3   4   0]]

  

 

  
1
  
2
  
3
  
4
  
5
  
6
  
7
  
8
 

词语的解释

importance_tfidf = get_most_important_features(tfidf_vectorizer, clf_tfidf, 10)

  

 

  
1
 

top_scores = [a[0] for a in importance_tfidf[1]['tops']]
top_words = [a[1] for a in importance_tfidf[1]['tops']]
bottom_scores = [a[0] for a in importance_tfidf[1]['bottom']]
bottom_words = [a[1] for a in importance_tfidf[1]['bottom']]

plot_important_words(top_scores, top_words, bottom_scores, bottom_words, "Most important words for relevance")

  

 

  
1
  
2
  
3
  
4
  
5
  
6
 

这些词看起来比之前强一些了

文章来源: maoli.blog.csdn.net，作者：刘润森！，版权归原作者所有，如需转载，请联系作者。

原文链接：maoli.blog.csdn.net/article/details/89455723