Optimize for loop so it takes less time - python

I have a data of 50000 rows and have to use the function on every row. So I am using for loop but it is taking too much time of around 1.5 hr. So can anyone please help me in order to make it quicker.
test_feat_custom = []
count = 0
for x in test_data['text']:
row = getFeatures(x)
test_feat_custom.append(row)
So time taken by this code to execute is too long so please help me to make it quicker.
This my getFeatures function code
import pandas as pd
import nltk
nltk.download('maxent_ne_chunker')
nltk.download('words')
from nltk.tokenize import word_tokenize
from nltk.tag import pos_tag
from nltk import pos_tag_sents
from nltk.tokenize import sent_tokenize
from nltk.chunk import ne_chunk
import collections
from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer
import numpy as np
import spacy
from collections import Counter
import en_core_web_sm
nlp = en_core_web_sm.load()
vad = pd.read_csv('/home/riteshjain/anaconda3/Api/vader_lexicon.txt', error_bad_lines=False, header = None, sep = ' ')
post = vad.copy()
post[1] = post[post[1] > 0][1]
post = post.dropna()
post = post.reset_index(drop=True)
vad[1] = vad[vad[1] < 0][1]
vad = vad.dropna()
vad = vad.reset_index(drop=True)
def Que_Counter(x):
que_c = x.count('?')
return que_c
def Exc_Counter(x):
exc_c = x.count('!')
return exc_c
def Sent_Counter(x):
tokenized_text=sent_tokenize(x)
return len(tokenized_text)
def Word_Counter(x):
tokenized_word = word_tokenize(x)
return len(tokenized_word)
def Noun_Counter(x):
tokenized_word = word_tokenize(x)
pos = pos_tag(tokenized_word)
nouns = []
for (word, pos) in pos:
if pos.startswith("NN"):
nouns.append(word)
return len(nouns)
def Pronoun_Counter(x):
tokenized_word = word_tokenize(x)
pos = pos_tag(tokenized_word)
pronouns = []
for (word, pos) in pos:
if pos.startswith("PRP"):
pronouns.append(word)
return len(pronouns)
def Adjective_Counter(x):
tokenized_word = word_tokenize(x)
pos = pos_tag(tokenized_word)
adject = []
for (word, pos) in pos:
if pos.startswith("JJ"):
adject.append(word)
return len(adject)
def Adverb_Counter(x):
tokenized_word = word_tokenize(x)
pos = pos_tag(tokenized_word)
adverb = []
for (word, pos) in pos:
if pos.startswith("RB"):
adverb.append(word)
return len(adverb)
def Name_Entity(x):
doc = nlp(x)
ca = [(X.text, X.label_) for X in doc.ents]
return len(ca)
def negation(x):
negat = ["aint", "arent", "cannot", "cant", "couldnt", "darent", "didnt", "doesnt",
"ain't", "aren't", "can't", "couldn't", "daren't", "didn't", "doesn't",
"dont", "hadnt", "hasnt", "havent", "isnt", "mightnt", "mustnt", "neither",
"don't", "hadn't", "hasn't", "haven't", "isn't", "mightn't", "mustn't",
"neednt", "needn't", "never", "none", "nope", "nor", "not", "nothing", "nowhere",
"oughtnt", "shant", "shouldnt", "uhuh", "wasnt", "werent",
"oughtn't", "shan't", "shouldn't", "uh-uh", "wasn't", "weren't",
"without", "wont", "wouldnt", "won't", "wouldn't", "rarely", "seldom", "despite"]
count = 0
tokenized_word = x.split()
for a in negat:
for b in tokenized_word:
if a == b:
count +=1
return count
def neg(x,y):
words = x.split()
n_count = 0
for c in y[0]:
for j in words:
if c == j:
n_count += 1
return n_count
def pos(x,y):
words = x.split()
p_count = 0
for c in y[0]:
for j in words:
if c == j:
p_count += 1
return p_count
def getFeatures(sentence):
# get data from the user
# extract all features
numQuestion = Que_Counter(sentence)
numExclamation= Exc_Counter(sentence)
numSent = Sent_Counter(sentence)
numWord = Word_Counter(sentence)
numNoun = Noun_Counter(sentence)
numPronoun = Pronoun_Counter(sentence)
numAdject = Adjective_Counter(sentence)
numAdverb = Adverb_Counter(sentence)
numEntity = Name_Entity(sentence)
numNegation = negation(sentence)
numPosOpinion = pos(sentence, post)
numNegOpinion = neg(sentence, vad)
features = [numQuestion, numExclamation, numSent, numWord, numNoun, numPronoun, numAdject, numAdverb, numEntity, numNegation, numPosOpinion, numNegOpinion]
return features

Related

what is the diffrence beetween the bleu score and the vaerage sentence of bleu score

i'm having a hard time finding the bleus core for my seq to seq model for the task of question generation , my questions are the following :
if i use the sentence bleu to find the score beetween each refrence and the output and then devide the total of these sentence-bleu scores by the len of the test data , will it be the same as the corpus bleu ?
and for the corpus bleu implemented in the code as the nltk corpus bleu ?
import ntpath
import sys
import codecs
import os
import math
import operator
import functools
def fetch_data(cand, ref):
references = []
if '.eng' in ref:
reference_file = codecs.open(ref, 'r', 'utf-8')
references.append(reference_file.readlines())
else:
for root, dirs, files in os.walk(ref):
for f in files:
reference_file = codecs.open(os.path.join(root, f), 'r', 'utf-8')
references.append(reference_file.readlines())
candidate_file = codecs.open(cand, 'r', 'utf-8')
candidate = candidate_file.readlines()
return candidate, references
def count_ngram(candidate, references, n):
clipped_count = 0
count = 0
r = 0
c = 0
for si in range(len(candidate)):
# Calculate precision for each sentence
ref_counts = []
ref_lengths = []
# Build dictionary of ngram counts
for reference in references:
ref_sentence = reference[si]
ngram_d = {}
words = ref_sentence.strip().split()
ref_lengths.append(len(words))
limits = len(words) - n + 1
# loop through the sentance consider the ngram length
for i in range(limits):
ngram = ' '.join(words[i:i+n]).lower()
if ngram in ngram_d.keys():
ngram_d[ngram] += 1
else:
ngram_d[ngram] = 1
ref_counts.append(ngram_d)
# candidate
cand_sentence = candidate[si]
cand_dict = {}
words = cand_sentence.strip().split()
limits = len(words) - n + 1
for i in range(0, limits):
ngram = ' '.join(words[i:i + n]).lower()
if ngram in cand_dict:
cand_dict[ngram] += 1
else:
cand_dict[ngram] = 1
clipped_count += clip_count(cand_dict, ref_counts)
count += limits
r += best_length_match(ref_lengths, len(words))
c += len(words)
if clipped_count == 0:
pr = 0
else:
pr = float(clipped_count) / count
bp = brevity_penalty(c, r)
return pr, bp
def clip_count(cand_d, ref_ds):
"""Count the clip count for each ngram considering all references"""
count = 0
for m in cand_d.keys():
m_w = cand_d[m]
m_max = 0
for ref in ref_ds:
if m in ref:
m_max = max(m_max, ref[m])
m_w = min(m_w, m_max)
count += m_w
return count
def best_length_match(ref_l, cand_l):
"""Find the closest length of reference to that of candidate"""
least_diff = abs(cand_l-ref_l[0])
best = ref_l[0]
for ref in ref_l:
if abs(cand_l-ref) < least_diff:
least_diff = abs(cand_l-ref)
best = ref
return best
def brevity_penalty(c, r):
if c > r:
bp = 1
else:
bp = math.exp(1-(float(r)/c))
return bp
def geometric_mean(precisions):
return (functools.reduce(operator.mul, precisions)) ** (1.0 / len(precisions))
def BLEU(candidate, references):
precisions = []
for i in range(4):
pr, bp = count_ngram(candidate, references, i+1)
precisions.append(pr)
bleu = geometric_mean(precisions) * bp
return bleu
if __name__ == "__main__":
candidate, references = fetch_data(sys.argv[1], sys.argv[2])
bleu = BLEU(candidate, references)
print (bleu)
I'm not sure about the implementation you show but for implementations strictly following the original paper such as NLTKs it would not be the same: https://github.com/nltk/nltk/blob/develop/nltk/translate/bleu_score.py#L123.
Using sentence-BLEU means basically calling corpus-BLEU with just a one-sentence-corpus, but the other way around doesn't work. The scores should not be drastically different but they do differ because of macro-average vs micro-average.
I used BLEU for Seq2Seq evaluation before and just used sentence-BLEU and it worked just fine.

Adaptive DBSCAN achievement

I am doing the DBSCAN clustering in python. I want to achieve an adaptive way to return the number of clusters by self calculating its eps and Minpts parameters. Below is my code.
import math
import copy
import numpy as np
import pandas as pd
from sklearn.cluster import DBSCAN
def loadDataSet(fileName, splitChar='\t'):
dataSet = []
with open(fileName) as fr:
for line in fr.readlines():
curline = line.strip().split(splitChar)
fltline = list(map(float, curline))
dataSet.append(fltline)
return dataSet
def dist(a,b):
return math.sqrt(math.pow(a[0]-b[0],2) + math.pow(a[1]-b[1],2))
def returnDk(matrix,k):
Dk = []
for i in range(len(matrix)):
Dk.append(matrix[i][k])
return Dk
def returnDkAverage(Dk):
sum = 0
for i in range(len(Dk)):
sum = sum + Dk[i]
return sum/len(Dk)
def CalculateDistMatrix(dataset):
DistMatrix = [[0 for j in range(len(dataset))] for i in range(len(dataset))]
for i in range(len(dataset)):
for j in range(len(dataset)):
DistMatrix[i][j] = dist(dataset[i], dataset[j])
return DistMatrix
def returnEpsCandidate(dataSet):
DistMatrix = CalculateDistMatrix(dataSet)
tmp_matrix = copy.deepcopy(DistMatrix)
for i in range(len(tmp_matrix)):
tmp_matrix[i].sort()
EpsCandidate = []
for k in range(1,len(dataSet)):
Dk = returnDk(tmp_matrix,k)
DkAverage = returnDkAverage(Dk)
EpsCandidate.append(DkAverage)
return EpsCandidate
def returnMinptsCandidate(DistMatrix,EpsCandidate):
MinptsCandidate = []
for k in range(len(EpsCandidate)):
tmp_eps = EpsCandidate[k]
tmp_count = 0
for i in range(len(DistMatrix)):
for j in range(len(DistMatrix[i])):
if DistMatrix[i][j] <= tmp_eps:
tmp_count = tmp_count + 1
MinptsCandidate.append(tmp_count/len(dataSet))
return MinptsCandidate
def returnClusterNumberList(dataset,EpsCandidate,MinptsCandidate):
np_dataset = np.array(dataset)
ClusterNumberList = []
for i in range(len(EpsCandidate)):
clustering = DBSCAN(eps= EpsCandidate[i],min_samples= MinptsCandidate[i]).fit(np_dataset)
num_clustering = max(clustering.labels_)
ClusterNumberList.append(num_clustering)
return ClusterNumberList
if __name__ == '__main__':
data = pd.read_csv('/Users/Desktop/Mic/recorder_test1/New folder/MFCCresultsforclustering/MFCCresultsforclustering.csv')
dataSet = data.iloc[:,0:13].values
EpsCandidate = returnEpsCandidate(dataSet)
DistMatrix = CalculateDistMatrix(dataSet)
MinptsCandidate = returnMinptsCandidate(DistMatrix,EpsCandidate)
ClusterNumberList = returnClusterNumberList(dataSet,EpsCandidate,MinptsCandidate)
print(EpsCandidate)
print(MinptsCandidate)
print('cluster number list is')
print(ClusterNumberList)
However, the output with the loading data set is all [-1]s. I am wondering where is the mistake. Am I right for this general direction? If not, how can I achieve the adaptive DBSCAN clustering?

Implementation of Okapi BM25 in python

I am trying to implement Okapi BM25 in python. While I have seen some tutorials how to do it, it seems I am stuck in the process.
So I have collection of documents (and has as columns 'id' and 'text') and queries (and has as columns 'id' and 'text'). I have done the pre-processing steps and I have my documents and queries as a list:
documents = list(train_docs['text']) #put the documents text to list
queries = list(train_queries_all['text']) #put the queries text to list
Then for BM25 I do this:
pip install rank_bm25
#calculate BM25
from rank_bm25 import BM25Okapi
bm25 = BM25Okapi(documents)
#compute the score
bm_score = BM25Okapi.get_scores(documents, query=queries)
But it wouldn't work.
Then I tried to do this:
import math
import numpy as np
from multiprocessing import Pool, cpu_count
nd = len(documents) # corpus_size = 3612 (I am not sure if this is necessary)
class BM25:
def __init__(self, documents, tokenizer=None):
self.corpus_size = len(documents)
self.avgdl = 0
self.doc_freqs = []
self.idf = {}
self.doc_len = []
self.tokenizer = tokenizer
if tokenizer:
documents = self._tokenize_corpus(documents)
nd = self._initialize(documents)
self._calc_idf(nd)
def _initialize(self, documents):
nd = {} # word -> number of documents with word
num_doc = 0
for document in documents:
self.doc_len.append(len(document))
num_doc += len(document)
frequencies = {}
for word in document:
if word not in frequencies:
frequencies[word] = 0
frequencies[word] += 1
self.doc_freqs.append(frequencies)
for word, freq in frequencies.items():
if word not in nd:
nd[word] = 0
nd[word] += 1
self.avgdl = num_doc / self.corpus_size
return nd
def _tokenize_corpus(self, documents):
pool = Pool(cpu_count())
tokenized_corpus = pool.map(self.tokenizer, documents)
return tokenized_corpus
def _calc_idf(self, nd):
raise NotImplementedError()
def get_scores(self, queries):
raise NotImplementedError()
def get_top_n(self, queries, documents, n=5):
assert self.corpus_size == len(documents), "The documents given don't match the index corpus!"
scores = self.get_scores(queries)
top_n = np.argsort(scores)[::-1][:n]
return [documents[i] for i in top_n]
class BM25T(BM25):
def __init__(self, documents, k1=1.5, b=0.75, delta=1):
# Algorithm specific parameters
self.k1 = k1
self.b = b
self.delta = delta
super().__init__(documents)
def _calc_idf(self, nd):
for word, freq in nd.items():
idf = math.log((self.corpus_size + 1) / freq)
self.idf[word] = idf
def get_scores(self, queries):
score = np.zeros(self.corpus_size)
doc_len = np.array(self.doc_len)
for q in queries:
q_freq = np.array([(doc.get(q) or 0) for doc in self.doc_freqs])
score += (self.idf.get(q) or 0) * (self.delta + (q_freq * (self.k1 + 1)) /
(self.k1 * (1 - self.b + self.b * doc_len / self.avgdl) + q_freq))
return score
and then I try to get the scores:
score = BM25.get_scores(self=documents, queries)
But I get as a meesage:
score = BM25.get_scores(self=documents, queries)
SyntaxError: positional argument follows keyword argument
Does anyone has an idea why there is this error? Thank you in advance.
1 ) tokenize corpus or send tokinizing function to class
2 ) send only queries to "get_scores" function
read official example
from rank_bm25 import BM25Okapi
corpus = [
"Hello there good man!",
"It is quite windy in London",
"How is the weather today?"
]
tokenized_corpus = [doc.split(" ") for doc in corpus]
bm25 = BM25Okapi(tokenized_corpus)
query = "windy London"
tokenized_query = query.split(" ")
doc_scores = bm25.get_scores(tokenized_query)
I suggest you to use fastbm25, which is more fast than other bm25 version.
`pip install fastbm25
usage
from fastbm25 import fastbm25
corpus = [
"How are you !",
"Hello Jack! Nice to meet you!",
"I am from China, I like math."
]
tokenized_corpus = [doc.lower().split(" ") for doc in corpus]
model = fastbm25(tokenized_corpus)
query = "where are you from".lower().split()
result = model.top_k_sentence(query,k=1)
print(result)
you can learn mroe from https://github.com/zhusleep/fastbm25

AttributeError: 'LdaModel' object has no attribute 'minimum_phi_value'

As I was just experimenting with NLP then I was working on sarcasm detection but in meanwhile I had put this code.
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)
But it is giving me the following error:
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'
Code for 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]
The overall code is found here overall code.
The minimum_phi_value is a property of LdaModel that is set when an instance is created and for some reason it hasn't been serialized (which is pretty strange, probably a bug).
To workaround this particular issue you can add
self.lda.minimum_phi_value = 0.01
... after self.lda loading or avoid saving/restoring the model if possible (i.e. always train it).
But I encourage you to examine the fields of self.lda before and after serialization to check they are identical.

python create genetic algorithm no convergence to maximum or minimum

Hello i need help for create genetic algorithme for converge to maximum or minimum value.
I develop a code for found maximum sentence ascii sum, but my code not converge to maximum, my code make "yoyo" value
like this picture :
matploltib output
i share my code :
import random
import statistics
EVOLUTION=[]
words = [
["Un", "Des", "Une", "On", "Elle"],
["a", "eu", "avait", "est", "était", "fut"],
["soif", "rouge"]
]
def individual(data):
#return tuple(random.choice(range(len(feature))) for feature in data)
return tuple(random.choice(range(len(feature))) for feature in data)
def population(data, initial=100):
return [individual(data) for i in range(initial)]
def fitness(individual, data):
chaine=sentence(individual,words)
somme = 0
for caractere in chaine:
somme = somme + ord(caractere)
print(chaine)
print(somme)
EVOLUTION.append(somme)
return somme
#return sum(data[i][individual[i]] for i in range(len(individual)))
def grade(population, data):
fit = [fitness(ind, data) for ind in population]
return statistics.mean(fit)
def mutate(ind, data):
gene = random.randrange(0, len(ind))
clone = list(ind)
clone[gene] = random.randrange(0, len(data[gene]))
#print(sentence(tuple(clone),words))
return tuple(clone)
def cross(mother, father):
return tuple(round(statistics.mean(genes)) for genes in zip(mother, father))
def sentence(individual, words):
return ' '.join([words[i][individual[i]] for i in range(len(words))])
def evolve(population, data, retain=0.0, random_select=0.00, mutation_rate=0.00):
def cmp_ind(ind):
return fitness(ind, data)
sorted_population = sorted(population, key=cmp_ind, reverse=True)
len_retained = round(len(population) * retain)
retained = sorted_population[:len_retained]
random_selected = [
ind
for ind in sorted_population[len_retained:]
if random.random() <= random_select
]
mutated = [
mutate(ind, data)
for ind in sorted_population[len_retained:]
if random.random() <= mutation_rate
]
children = [
cross(random.choice(sorted_population),
random.choice(sorted_population))
for i in range(len(population) - len(random_selected) - len(mutated))
]
return random_selected + mutated + children
if __name__ == '__main__':
data = [[len(w) for w in ws] for ws in words]
initial_population = population(data, 30)
next_population = initial_population
max_iter = 3
for i in range(max_iter):
next_population = evolve(next_population, data)
sorted_population = sorted(next_population, key=lambda x: fitness(x, data))
best_individual = sorted_population[0]
print("best solution :")
chaine=sentence(best_individual,words)
somme = 0
for caractere in chaine:
somme = somme + ord(caractere)
print(chaine)
print(somme)
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
plt.plot(EVOLUTION)
plt.savefig('myfig')
i want to found highter solution in my fitness function
thanks for advance for your help

Categories