Yash Sonar Yash-567

## index.html
<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <meta http-equiv="X-UA-Compatible" content="IE=edge">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <script src="https://d3js.org/d3.v6.js"></script>
    <title></title>
</head>
<body>

## index.html
<!DOCTYPE html>
<meta charset="utf-8">

<!-- Load d3.js -->
<script src="https://d3js.org/d3.v4.js"></script>

<!-- Create a div where the circle will take place -->
<div id="dataviz_brushZoom"></div>

<script>

## d3.js
// https://d3js.org v7.0.1 Copyright 2010-2021 Mike Bostock
(function (global, factory) {
typeof exports === 'object' && typeof module !== 'undefined' ? factory(exports) :
typeof define === 'function' && define.amd ? define(['exports'], factory) :
(global = typeof globalThis !== 'undefined' ? globalThis : global || self, factory(global.d3 = global.d3 || {}));
}(this, (function (exports) { 'use strict';

var version = "7.0.1";

function ascending$3(a, b) {

## keras_recommendation_generate
model_2 = Model(input=model.get_layer('input_2').input, output = model.get_layer('embedding_2').output)
user_movie_embeddings = model_2.predict(x = usrc) # usrc = array of movie id liked by user
user_movie_embeddings = user_movie_embeddings.reshape(len(usrc),10)
user_movie_bias = np.array([5 for temp in range(len(usrc))])

user_embedding, residuals, rank, s = np.linalg.lstsq(user_movie_embeddings,user_movie_bias, rcond=-1) # Get embedding for new user
user_embedding = user_embedding.reshape(1, 10) # User embedding based on choices of user

## keras_recommendation_train.py
mc = keras.callbacks.ModelCheckpoint('weights{epoch:01d}.h5', period=1)
r = model.fit(
  x=[df_train.userId.values, df_train.movie_idx.values],
  y=df_train.rating.values - mu,
  epochs=epochs,
  batch_size=128,
  validation_data=(
    [df_test.userId.values, df_test.movie_idx.values],
    df_test.rating.values - mu
  ),

## keras_recommendation_compile.py
model.compile(
  loss='mse',
  optimizer=SGD(lr=0.08, momentum=0.9),
  metrics=['mse'],
)

## pytorch_show.py
from sklearn.utils import shuffle
from torch import nn
import torch
import torch.nn.functional as F

N = df.userId.max() + 1 # number of users
M = df.movie_idx.max() + 1 # number of movies

# split into train and test
df = shuffle(df, random_state = 12)

## keras_recommendation_model.py
# keras model
u = Input(shape=(1,))
m = Input(shape=(1,))
u_embedding = Embedding(N, K)(u) # (N, 1, K)
m_embedding = Embedding(M, K)(m) # (N, 1, K)
u_embedding = Flatten()(u_embedding) # (N, K)
m_embedding = Flatten()(m_embedding) # (N, K)
x = Concatenate()([u_embedding, m_embedding]) # (N, 2K)

x = Dense(400)(x)

## train_model.py
import random
from tqdm import tqdm

train_losses, test_losses = [], []

for e in range(epochs):
   running_loss = 0
   for i in tqdm(range(0, len(df_train), 128)):
      train = df_train[i:i+128]
      optimizer.zero_grad()

## optim_model.py
from torch import optim

criterion = nn.MSELoss()
optimizer = optim.SGD(model.parameters(), lr = 0.08, momentum=0.9)
	<!DOCTYPE html>
	<html lang="en">
	<head>
	<meta charset="UTF-8">
	<meta http-equiv="X-UA-Compatible" content="IE=edge">
	<meta name="viewport" content="width=device-width, initial-scale=1.0">
	<script src="https://d3js.org/d3.v6.js"></script>
	<title></title>
	</head>
	<body>
	<!DOCTYPE html>
	<meta charset="utf-8">

	<!-- Load d3.js -->
	<script src="https://d3js.org/d3.v4.js"></script>

	<!-- Create a div where the circle will take place -->
	<div id="dataviz_brushZoom"></div>

	<script>
	// https://d3js.org v7.0.1 Copyright 2010-2021 Mike Bostock
	(function (global, factory) {
	typeof exports === 'object' && typeof module !== 'undefined' ? factory(exports) :
	typeof define === 'function' && define.amd ? define(['exports'], factory) :
	(global = typeof globalThis !== 'undefined' ? globalThis : global \|\| self, factory(global.d3 = global.d3 \|\| {}));
	}(this, (function (exports) { 'use strict';

	var version = "7.0.1";

	function ascending$3(a, b) {
	model_2 = Model(input=model.get_layer('input_2').input, output = model.get_layer('embedding_2').output)
	user_movie_embeddings = model_2.predict(x = usrc) # usrc = array of movie id liked by user
	user_movie_embeddings = user_movie_embeddings.reshape(len(usrc),10)
	user_movie_bias = np.array([5 for temp in range(len(usrc))])

	user_embedding, residuals, rank, s = np.linalg.lstsq(user_movie_embeddings,user_movie_bias, rcond=-1) # Get embedding for new user
	user_embedding = user_embedding.reshape(1, 10) # User embedding based on choices of user
	mc = keras.callbacks.ModelCheckpoint('weights{epoch:01d}.h5', period=1)
	r = model.fit(
	x=[df_train.userId.values, df_train.movie_idx.values],
	y=df_train.rating.values - mu,
	epochs=epochs,
	batch_size=128,
	validation_data=(
	[df_test.userId.values, df_test.movie_idx.values],
	df_test.rating.values - mu
	),
	model.compile(
	loss='mse',
	optimizer=SGD(lr=0.08, momentum=0.9),
	metrics=['mse'],
	)
	from sklearn.utils import shuffle
	from torch import nn
	import torch
	import torch.nn.functional as F

	N = df.userId.max() + 1 # number of users
	M = df.movie_idx.max() + 1 # number of movies

	# split into train and test
	df = shuffle(df, random_state = 12)
	# keras model
	u = Input(shape=(1,))
	m = Input(shape=(1,))
	u_embedding = Embedding(N, K)(u) # (N, 1, K)
	m_embedding = Embedding(M, K)(m) # (N, 1, K)
	u_embedding = Flatten()(u_embedding) # (N, K)
	m_embedding = Flatten()(m_embedding) # (N, K)
	x = Concatenate()([u_embedding, m_embedding]) # (N, 2K)

	x = Dense(400)(x)
	import random
	from tqdm import tqdm

	train_losses, test_losses = [], []

	for e in range(epochs):
	running_loss = 0
	for i in tqdm(range(0, len(df_train), 128)):
	train = df_train[i:i+128]
	optimizer.zero_grad()
	from torch import optim

	criterion = nn.MSELoss()
	optimizer = optim.SGD(model.parameters(), lr = 0.08, momentum=0.9)