Поскольку я просто экспериментировал с НЛП, я работал над обнаружением сарказма, но в то же время я добавил этот код.
sarcasmextractor.py
# coding: utf-8
# Importing the library
# In[2]:
import io
import sys
import os
import numpy as np
import pandas as pd
import nltk
import gensim
import csv, collections
from textblob import TextBlob
from sklearn.utils import shuffle
from sklearn.svm import LinearSVC
from sklearn.metrics import classification_report
from sklearn.feature_extraction import DictVectorizer
import pickle
import replace_emoji
# Define a class to load the SentimentWordnet and write methods to calculate the scores
# In[4]:
class load_senti_word_net(object):
"""
constructor to load the file and read the file as CSV
6 columns - pos, ID, PosScore, NegScore, synsetTerms, gloss
synsetTerms can have multiple similar words like abducting#1 abducent#1 and will read each one and calculaye the scores
"""
def __init__(self):
sent_scores = collections.defaultdict(list)
with io.open("SentiWordNet_3.0.0_20130122.txt") as fname:
file_content = csv.reader(fname, delimiter='\t',quotechar='"')
for line in file_content:
if line[0].startswith('#') :
continue
pos, ID, PosScore, NegScore, synsetTerms, gloss = line
for terms in synsetTerms.split(" "):
term = terms.split("#")[0]
term = term.replace("-","").replace("_","")
key = "%s/%s"%(pos,term.split("#")[0])
try:
sent_scores[key].append((float(PosScore),float(NegScore)))
except:
sent_scores[key].append((0,0))
for key, value in sent_scores.items():
sent_scores[key] = np.mean(value,axis=0)
self.sent_scores = sent_scores
"""
For a word,
nltk.pos_tag(["Suraj"])
[('Suraj', 'NN')]
"""
def score_word(self, word):
pos = nltk.pos_tag([word])[0][1]
return self.score(word, pos)
def score(self,word, pos):
"""
Identify the type of POS, get the score from the senti_scores and return the score
"""
if pos[0:2] == 'NN':
pos_type = 'n'
elif pos[0:2] == 'JJ':
pos_type = 'a'
elif pos[0:2] =='VB':
pos_type='v'
elif pos[0:2] =='RB':
pos_type = 'r'
else:
pos_type = 0
if pos_type != 0 :
loc = pos_type+'/'+word
score = self.sent_scores[loc]
if len(score)>1:
return score
else:
return np.array([0.0,0.0])
else:
return np.array([0.0,0.0])
"""
Repeat the same for a sentence
nltk.pos_tag(word_tokenize("My name is Suraj"))
[('My', 'PRP$'), ('name', 'NN'), ('is', 'VBZ'), ('Suraj', 'NNP')]
"""
def score_sentencce(self, sentence):
pos = nltk.pos_tag(sentence)
print (pos)
mean_score = np.array([0.0, 0.0])
for i in range(len(pos)):
mean_score += self.score(pos[i][0], pos[i][1])
return mean_score
def pos_vector(self, sentence):
pos_tag = nltk.pos_tag(sentence)
vector = np.zeros(4)
for i in range(0, len(pos_tag)):
pos = pos_tag[i][1]
if pos[0:2]=='NN':
vector[0] += 1
elif pos[0:2] =='JJ':
vector[1] += 1
elif pos[0:2] =='VB':
vector[2] += 1
elif pos[0:2] == 'RB':
vector[3] += 1
return vector
# Now let's extract the features
#
# ###Stemming and Lemmatization
# In[5]:
porter = nltk.PorterStemmer()
sentiments = load_senti_word_net()
# In[7]:
def gram_features(features,sentence):
sentence_rep = replace_emoji.replace_reg(str(sentence))
token = nltk.word_tokenize(sentence_rep)
token = [porter.stem(i.lower()) for i in token]
bigrams = nltk.bigrams(token)
bigrams = [tup[0] + ' ' + tup[1] for tup in bigrams]
grams = token + bigrams
#print (grams)
for t in grams:
features['contains(%s)'%t]=1.0
# In[8]:
import string
def sentiment_extract(features, sentence):
sentence_rep = replace_emoji.replace_reg(sentence)
token = nltk.word_tokenize(sentence_rep)
token = [porter.stem(i.lower()) for i in token]
mean_sentiment = sentiments.score_sentencce(token)
features["Positive Sentiment"] = mean_sentiment[0]
features["Negative Sentiment"] = mean_sentiment[1]
features["sentiment"] = mean_sentiment[0] - mean_sentiment[1]
#print(mean_sentiment[0], mean_sentiment[1])
try:
text = TextBlob(" ".join([""+i if i not in string.punctuation and not i.startswith("'") else i for i in token]).strip())
features["Blob Polarity"] = text.sentiment.polarity
features["Blob Subjectivity"] = text.sentiment.subjectivity
#print (text.sentiment.polarity,text.sentiment.subjectivity )
except:
features["Blob Polarity"] = 0
features["Blob Subjectivity"] = 0
print("do nothing")
first_half = token[0:int(len(token)/2)]
mean_sentiment_half = sentiments.score_sentencce(first_half)
features["positive Sentiment first half"] = mean_sentiment_half[0]
features["negative Sentiment first half"] = mean_sentiment_half[1]
features["first half sentiment"] = mean_sentiment_half[0]-mean_sentiment_half[1]
try:
text = TextBlob(" ".join([""+i if i not in string.punctuation and not i.startswith("'") else i for i in first_half]).strip())
features["first half Blob Polarity"] = text.sentiment.polarity
features["first half Blob Subjectivity"] = text.sentiment.subjectivity
#print (text.sentiment.polarity,text.sentiment.subjectivity )
except:
features["first Blob Polarity"] = 0
features["first Blob Subjectivity"] = 0
print("do nothing")
second_half = token[int(len(token)/2):]
mean_sentiment_sechalf = sentiments.score_sentencce(second_half)
features["positive Sentiment second half"] = mean_sentiment_sechalf[0]
features["negative Sentiment second half"] = mean_sentiment_sechalf[1]
features["second half sentiment"] = mean_sentiment_sechalf[0]-mean_sentiment_sechalf[1]
try:
text = TextBlob(" ".join([""+i if i not in string.punctuation and not i.startswith("'") else i for i in second_half]).strip())
features["second half Blob Polarity"] = text.sentiment.polarity
features["second half Blob Subjectivity"] = text.sentiment.subjectivity
#print (text.sentiment.polarity,text.sentiment.subjectivity )
except:
features["second Blob Polarity"] = 0
features["second Blob Subjectivity"] = 0
print("do nothing")
# In[9]:
features = {}
sentiment_extract(features,"a long narrow opening")
# In[11]:
def pos_features(features,sentence):
sentence_rep = replace_emoji.replace_reg(sentence)
token = nltk.word_tokenize(sentence_rep)
token = [ porter.stem(each.lower()) for each in token]
pos_vector = sentiments.pos_vector(token)
for j in range(len(pos_vector)):
features['POS_'+str(j+1)] = pos_vector[j]
print ("done")
# In[12]:
features = {}
pos_features(features,"a long narrow opening")
# In[13]:
def capitalization(features,sentence):
count = 0
for i in range(len(sentence)):
count += int(sentence[i].isupper())
features['Capitalization'] = int(count > 3)
print (count)
# In[14]:
features = {}
capitalization(features,"A LoNg NArrow opening")
# In[15]:
import topic
topic_mod = topic.topic(nbtopic=200,alpha='symmetric')
# In[16]:
topic_mod = topic.topic(model=os.path.join('topics.tp'),dicttp=os.path.join('topics_dict.tp'))
# In[17]:
def topic_feature(features,sentence,topic_modeler):
topics = topic_modeler.transform(sentence)
for j in range(len(topics)):
features['Topic :'] = topics[j][1]
# In[18]:
topic_feature(features,"A LoNg NArrow opening",topic_mod)
# In[19]:
def get_features(sentence, topic_modeler):
features = {}
gram_features(features,sentence)
pos_features(features,sentence)
sentiment_extract(features, sentence)
capitalization(features,sentence)
topic_feature(features, sentence,topic_modeler)
return features
# In[20]:
df = pd.DataFrame()
df = pd.read_csv("dataset_csv.csv", header=0, sep='\t')
df.head()
# In[17]:
import re
for i in range(0,df.size):
temp = str(df["tweets"][i])
temp = re.sub(r'[^\x00-\x7F]+','',temp)
featureset.append((get_features(temp,topic_mod), df["label"][i]))
# In[20]:
c = []
for i in range(0,len(featureset)):
c.append(pd.DataFrame(featureset[i][0],index=[i]))
result = pd.concat(c)
# In[22]:
result.insert(loc=0,column="label",value='0')
# In[23]:
for i in range(0, len(featureset)):
result["label"].loc[i] = featureset[i][1]
# In[25]:
result.to_csv('feature_dataset.csv')
# In[3]:
df = pd.DataFrame()
df = pd.read_csv("feature_dataset.csv", header=0)
df.head()
# In[4]:
get_ipython().magic('matplotlib inline')
import matplotlib as matplot
import seaborn
result = df
# In[5]:
X = result.drop(['label','Unnamed: 0','Topic :'],axis=1).values
# In[6]:
Y = result['label']
# In[7]:
import pickle
import pefile
import sklearn.ensemble as ek
from sklearn import cross_validation, tree, linear_model
from sklearn.feature_selection import SelectFromModel
from sklearn.externals import joblib
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import confusion_matrix
from sklearn.pipeline import make_pipeline
from sklearn import preprocessing
from sklearn import svm
from sklearn.linear_model import LinearRegression
import sklearn.linear_model as lm
# In[29]:
model = { "DecisionTree":tree.DecisionTreeClassifier(max_depth=10),
"RandomForest":ek.RandomForestClassifier(n_estimators=50),
"Adaboost":ek.AdaBoostClassifier(n_estimators=50),
"GradientBoosting":ek.GradientBoostingClassifier(n_estimators=50),
"GNB":GaussianNB(),
"Logistic Regression":LinearRegression()
}
# In[8]:
X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, Y ,test_size=0.2)
# In[9]:
X_train = pd.DataFrame(X_train)
X_train = X_train.fillna(X_train.mean())
X_test = pd.DataFrame(X_test)
X_test = X_test.fillna(X_test.mean())
# In[38]:
results_algo = {}
for algo in model:
clf = model[algo]
clf.fit(X_train,y_train.astype(int))
score = clf.score(X_test,y_test.astype(int))
print ("%s : %s " %(algo, score))
results_algo[algo] = score
# In[39]:
winner = max(results_algo, key=results_algo.get)
# In[40]:
clf = model[winner]
res = clf.predict(X_test)
mt = confusion_matrix(y_test, res)
print("False positive rate : %f %%" % ((mt[0][1] / float(sum(mt[0])))*100))
print('False negative rate : %f %%' % ( (mt[1][0] / float(sum(mt[1]))*100)))
# In[41]:
from sklearn import metrics
print (metrics.classification_report(y_test, res))
# In[34]:
test_data = "public meetings are awkard for me as I can insult people but I choose not to and that is something that I find difficult to live with"
# In[101]:
test_data="I purchased this product 4.47 billion years ago and when I opened it today, it was half empty."
# In[82]:
test_data="when people see me eating and ask me are you eating? No no I'm trying to choke myself to death #sarcastic"
# In[102]:
test_feature = []
test_feature.append((get_features(test_data,topic_mod)))
# In[104]:
test_feature
# In[105]:
c = []
c.append(pd.DataFrame(test_feature[0],index=[i]))
test_result = pd.concat(c)
test_result = test_result.drop(['Topic :'],axis=1).values
# In[106]:
res= clf.predict(test_result)
Но выдает следующую ошибку:
C:\ProgramData\Anaconda3\lib\site-packages\gensim\utils.py:1197: UserWarning: detected Windows; aliasing chunkize to chunkize_serial
warnings.warn("detected Windows; aliasing chunkize to chunkize_serial")
[('a', 'DT'), ('long', 'JJ'), ('narrow', 'JJ'), ('open', 'JJ')]
[('a', 'DT'), ('long', 'JJ')]
[('narrow', 'JJ'), ('open', 'JJ')]
done
5
Traceback (most recent call last):
File "C:\shubhamprojectwork\sarcasm detection\SarcasmDetection-master\SarcasmDetection-master\Code\sarcasm-extraction.py", line 276, in <module>
topic_feature(features,"A LoNg NArrow opening",topic_mod)
File "C:\shubhamprojectwork\sarcasm detection\SarcasmDetection-master\SarcasmDetection-master\Code\sarcasm-extraction.py", line 268, in topic_feature
topics = topic_modeler.transform(sentence)
File "C:\shubhamprojectwork\sarcasm detection\SarcasmDetection-master\SarcasmDetection-master\Code\topic.py", line 42, in transform
return self.lda[corpus_sentence]
File "C:\ProgramData\Anaconda3\lib\site-packages\gensim\models\ldamodel.py", line 1160, in __getitem__
return self.get_document_topics(bow, eps, self.minimum_phi_value, self.per_word_topics)
AttributeError: 'LdaModel' object has no attribute 'minimum_phi_value'
Код для topic.py:
from gensim import corpora, models, similarities
import nltk
from nltk.corpus import stopwords
import numpy as np
import pandas as pd
import replace_emoji
class topic(object):
def __init__(self, nbtopic = 100, alpha=1,model=None,dicttp=None):
self.nbtopic = nbtopic
self.alpha = alpha
self.porter = nltk.PorterStemmer()
self.stop = stopwords.words('english')+['.','!','?','"','...','\\',"''",'[',']','~',"'m","'s",';',':','..','$']
if model!=None and dicttp!=None:
self.lda = models.ldamodel.LdaModel.load(model)
self.dictionary = corpora.Dictionary.load(dicttp)
def fit(self,documents):
documents_mod = documents
tokens = [nltk.word_tokenize(sentence) for sentence in documents_mod]
tokens = [[self.porter.stem(t.lower()) for t in sentence if t.lower() not in self.stop] for sentence in tokens]
self.dictionary = corpora.Dictionary(tokens)
corpus = [self.dictionary.doc2bow(text) for text in tokens]
self.lda = models.ldamodel.LdaModel(corpus,id2word=self.dictionary, num_topics=self.nbtopic,alpha=self.alpha)
self.lda.save('topics.tp')
self.dictionary.save('topics_dict.tp')
def get_topic(self,topic_number):
return self.lda.print_topic(topic_number)
def transform(self,sentence):
sentence_mod = sentence
tokens = nltk.word_tokenize(sentence_mod)
tokens = [self.porter.stem(t.lower()) for t in tokens if t.lower() not in self.stop]
corpus_sentence = self.dictionary.doc2bow(tokens)
return self.lda[corpus_sentence]
Общий код находится здесь Общий код .