ajaymuktha

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

ajaymuktha

y_pred = regressor.predict(X_test)
print(r2_score(Y_test,y_pred))

ajaymuktha

from sklearn.linear_model import LinearRegression
from sklearn.metrics import r2_score
regressor = LinearRegression()   
regressor.fit(X_train,Y_train)

ajaymuktha

from sklearn.model_selection import train_test_split 
X_train,X_test,Y_train,Y_test = train_test_split(X,Y, test_size=0.2, random_state = 0)  

ajaymuktha

from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_X = LabelEncoder()
X[:,3] = labelencoder_X.fit_transform(X[:,3])
onehotencoder = OneHotEncoder(categorical_features = [3])
X=onehotencoder.fit_transform(X).toarray()

ajaymuktha

dataset = pd.read_csv('Startups.csv')
X = dataset.iloc[:,:-1].values
Y = dataset.iloc[:,4].values 

ajaymuktha

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

ajaymuktha

sentences = nltk.sent_tokenize(text)

ajaymuktha

text = re.sub(r'\[[0-9]*\]',' ',text)
text = re.sub(r'\s+',' ',text)
text = text.lower()
text = re.sub(r'\d',' ',text)

ajaymuktha

import nltk
import urllib
import bs4 as bs
import pandas as pd
import re
from nltk.corpus import stopwords
nltk.download('stopwords')