Abhayparashar31

import gensim
import re
from gensim.summarization.summarizer import summarize
import requests
from bs4 import BeautifulSoup

url = 'https://en.wikipedia.org/wiki/Python_(programming_language)'

res = requests.get(url)
soup = BeautifulSoup(res.text,'html.parser')

Abhayparashar31

def get_key(val): 
    for key, value in sentences_score.items(): 
        if val == value: 
            return key 
key = get_key(max(sentences_score.values()))
summary = heapq.nlargest(n,sentences_score,key=sentences_score.get)  ## n=3
print(" ".join(summary))

Abhayparashar31

sentences_score = {}
for sentence in sent_tokens:
    for word in word_tokenize(sentence):
        if word in word_frequency.keys():
            if (len(sentence.split(" "))) <30:
                if sentence not in sentences_score.keys():
                    sentences_score[sentence] = word_frequency[word]
                else:
                    sentences_score[sentence] += word_frequency[word]

Abhayparashar31

import nltk
nltk.download('punkt')
nltk.download('stopwords')
from nltk.tokenize import sent_tokenize,word_tokenize

sent_tokens = sent_tokenize(cleaned_data)
word_tokens = word_tokenize(cleaned_data)
word_frequency = {}
stopwords =  set(stopwords.words("english"))

Abhayparashar31

import re
def clean_data(data):
  text = re.sub(r"\[[0-9]*\]"," ",data)
  text = text.lower()
  text = re.sub(r'\s+'," ",text)
  text = re.sub(r","," ",text)
  return text
cleaned_data = clean_data(raw_data)

Abhayparashar31

from bs4 import BeautifulSoup
import requests

def scrape_con(url):
  res = requests.get(url)
  soup = BeautifulSoup(res.text,'html.parser') 
  content = soup.findAll("p")
  data = ""
  for text in content:
    data +=text.text

Abhayparashar31

import xgboost as xgb
from sklearn.model_selection import RandomizedSearchCV

params = {'max_depth': [3, 6, 8,10,12],
          'learning_rate': [0.01, 0.1, 0.2, 0.001, 0.3],
          'colsample_bytree': np.arange(0.3, 1.0, 0.1),
          'colsample_bylevel': np.arange(0.3, 1.0, 0.1),
          'subsample': np.arange(0.3, 1.0, 0.1),
          'n_estimators': [100, 150, 200, 250,300]
          }

Abhayparashar31

import numpy as np
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

## Base Models
from sklearn.neighbors import KNeighborsClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.svm import SVC

Abhayparashar31

from sklearn.neighbors import KNeighborsClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.svm import SVC
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import StackingClassifier

base_learners = [
                 ('l1', KNeighborsClassifier()),
                 ('l2', DecisionTreeClassifier()),
                 ('l3',SVC(gamma=2, C=1)))

Abhayparashar31

from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import AdaBoostClassifier

dt = DecisionTreeClassifier(max_depth=2, random_state=0)
adc = AdaBoostClassifier(base_estimator=dt, n_estimators=7, learning_rate=0.1, random_state=0)

adc.fit(x_train, y_train)