khuangaf

from googleapiclient.discovery import build

# developer keys for Youtube V3 API
DEVELOPER_KEY = 'YOUR_API_KEY'
YOUTUBE_API_SERVICE_NAME = "youtube"
YOUTUBE_API_VERSION = "v3"

# creating youtube resource object for interacting with api
youtube = build(YOUTUBE_API_SERVICE_NAME,
                YOUTUBE_API_VERSION,

khuangaf

# coding: utf-8

# In[1]:


import cv2
import pandas as pd
import numpy as np
import os

khuangaf

maxlen = 75
output_size = y_train.shape[1]
max_features= output_size
embed_size = 50
input_size = (maxlen, 1,)
def get_model():
    global input_size, output_size
    inp = Input(shape=input_size)
    x = Embedding(max_features, embed_size)(inp)
    x = CuDNNGRU(50, return_sequences=True)(inp)

khuangaf

item_index = { str(i):i for i in range(931)}
embeddings_index={}
f = open( 'data/item_vectors.txt')
for line in f:
    values = line.split()
    word = values[0]
    coefs = np.asarray(values[1:], dtype='float32')
    embeddings_index[word] = coefs
f.close()

khuangaf

from gensim.models import Word2Vec
model = Word2Vec(item_list, size=50, window=5, min_count=5, workers=10, sg=0)
model.wv.save_word2vec_format('data/item_vectors.txt')

khuangaf

from spotlight.sequence.implicit import ImplicitSequenceModel
sequential_interaction = implicit_interactions.to_sequence()
implicit_sequence_model = ImplicitSequenceModel()
implicit_sequence_model.fit(sequential_interaction)

khuangaf

from spotlight.factorization.implicit import ImplicitFactorizationModel
implicit_model = ImplicitFactorizationModel()
implicit_model.fit(implicit_interactions)
implicit_model.predict(user_ids, item_ids=None)

khuangaf

from spotlight.interactions import Interactions

implicit_interactions = Interactions(user_ids, item_ids)
explicit_interactions = Interactions(user_ids, item_ids, ratings)

khuangaf

model_ted.wv.most_similar("Gastroenteritis")

khuangaf

model_ted.wv.most_similar(“shht”)