megha444

from matplotlib import pyplot as pt
x = [7,12,3]
y = [1,16,6]
pt.plot(x,y)
pt.title('Info')
pt.ylabel('Y axis')
pt.xlabel('X axis')
pt.show()

megha444

import pandas as pd
ds=pd.read_csv('train.csv')
ds.head()
ds.shape()

megha444

import nltk
from nltk.tokenize import word_tokenize
nltk.download ('punkt')
text = "This is a sample text to show word tokenization"
print(word_tokenize(text))

megha444

import keras
from keras.layers import Dense, Activation
from keras.models import Sequential
import matplotlib.pyplot as plt 
import numpy as np

xx = ipdata = np.linspace(1,2,100)
yy = xx*4 + np.random.randn(*xx.shape) * 0.3

megha444

import theano
from theano import tensor
m = tensor.dscalar()
n = tensor.dscalar()
p = a + b
q = theano.function([m,n], p)
r = q(1.5, 2.5)
print (r)

megha444

import numpy as np
from sklearn.preprocessing import MinMaxScaler
demo = np.random.randint(10, 200, (20 ,2))
scalarModel = MinMaxScaler()
scalarModel.fit_transform(demo)
scalarModel = MinMaxScaler()
featureData = scalarModel.fit_transform(demo)
import pandas as pan
data = pan.DataFrame(data=featureData, columns=['c1', 'c2', 'c3', 'label'])
X = data[['c1', 'c2', 'c3']]

megha444

import numpy as np
#Array object creation
num_array = np.array( [[3,2,1], 
[7,1,5]] ) 

# Printing array object type
print("Array type is: ", type(num_array)) 

#Array dimensions 
print("Number of dimensions: ", num_array.ndim) 

megha444

#load weights of best model
pathw = 'saved_weights.pt'
model_def.load_state_dict(torch.load(pathw))
#FINE TUNE FOR TEST DATA
# get predictions for test data
with torch.no_grad():
  pred = model_def(testseq.to(device), testmask.to(device))
  pred = pred.detach().cpu().numpy()

#TO CHECK MODEL PERFORMANCE

megha444

# function to train the model
def train():
  
  model_def.train()

  totalloss, totalaccuracy = 0, 0
  
  # empty list to save model predictions
  totalpreds=[]
  

megha444

from sklearn.utils.class_weight import compute_class_weight

#compute class weights
classw = compute_class_weight('balanced', np.unique(train_labels), trainlabels)

print("Class Weights:",classweights)

#Output obtained: [0.57743559 3.72848948]

# converting list of class weights to a tensor