grohith327

from tpot import TPOTClassifier
from sklearn.datasets import load_digits
from sklearn.model_selection import train_test_split

digits = load_digits()
x_train, x_test, y_train, y_test = train_test_split(digits.data,digits.target,train_size=0.75,test_size=0.25)

clf = TPOTClassifier(generations=10, population_size=20, verbosity=2)
clf.fit(x_train,y_train)
print(clf.score(x_test,y_test))

grohith327

import pandas as pd
import numpy as np

df = pd.read_csv("/Users/rohith/Documents/Datasets/Tesla_Stock_prices/Tesla_Stock.csv") # read csv file

rows = df.values.tolist()  # convert dataframe into a list
rows.reverse()

grohith327

# Linear Regression model
from sklearn.linear_model import LinearRegression 
clf_lr = LinearRegression()
clf_lr.fit(x_train,y_train)
y_pred_lr = clf_lr.predict(x_test)

# Support Vector Machine with a Radial Basis Function as kernel 
from sklearn.svm import SVR
clf_svr = SVR(kernel='rbf', C=1e3, gamma=0.1)
clf_svr.fit(x_train,y_train)

grohith327

import matplotlib.pyplot as plt 

f,(ax1,ax2) = plt.subplots(1,2,figsize=(30,10))

# Linear Regression
ax1.scatter(range(len(y_test)),y_test,label='data')
ax1.plot(range(len(y_test)),y_pred_lr,color='green',label='LR model')
ax1.legend()

# Support Vector Machine

grohith327

print("Accuracy of Linear Regerssion Model:",clf_lr.score(x_test,y_test))
print("Accuracy of SVM-RBF Model:",clf_svr.score(x_test,y_test))
print("Accuracy of Random Forest Model:",clf_rf.score(x_test,y_test))
print("Accuracy of Gradient Boosting Model:",clf_gb.score(x_test,y_test))

grohith327

with open("/Users/rohith/Documents/Datasets/sentiment_labelled_sentences/amazon_cells_labelled.txt") as f1:
    lines = f1.readlines()

with open("/Users/rohith/Documents/Datasets/sentiment_labelled_sentences/imdb_labelled.txt") as f1:
    temp = f1.readlines()
    lines=lines+temp

with open("/Users/rohith/Documents/Datasets/sentiment_labelled_sentences/yelp_labelled.txt") as f1:
    temp = f1.readlines()
    lines=lines+temp

grohith327

x = []
y = []
for value in lines:
    temp = value.split('\t')
    x.append(temp[0])
    temp[1].replace('\n','')
    y.append(int(temp[1]))

grohith327

from keras.preprocessing.text import Tokenizer

tokenizer = Tokenizer(num_words=2500,split=' ')
tokenizer.fit_on_texts(x)

grohith327

from keras.preprocessing.sequence import pad_sequences

X = tokenizer.texts_to_sequences(x)
X = pad_sequences(X)

grohith327

import keras 
from keras.layers import Embedding, LSTM, Dense
from keras.models import Sequential

model = Sequential()
model.add(Embedding(2500,128,input_length=X.shape[1],dropout=0.2))
model.add(LSTM(300, dropout_U=0.2,dropout_W=0.2))
model.add(Dense(2,activation='softmax'))

model.compile(loss=keras.losses.categorical_crossentropy,optimizer='adam',metrics=['accuracy'])