gaphex

from nltk.corpus import reuters

nltk.download("reuters")
nltk.download("punkt")

max_samples = 256
categories = ['wheat', 'tea', 'strategic-metal', 
              'housing', 'money-supply', 'fuel']

S, X, Y = [], [], []

gaphex

Q = tf.placeholder("float", [dim])
S = tf.placeholder("float", [None, dim])
S_norm = tf.placeholder("float", [None, 1])

Qr = tf.reshape(Q, (1, -1))

PP = S_norm
QQ = tf.matmul(Qr, tf.transpose(Qr))
PQ = tf.matmul(S, tf.transpose(Qr))

gaphex

class L2Retriever:
    def __init__(self, dim, top_k=3, use_norm=False, use_gpu=True):
        self.dim = dim
        self.top_k = top_k
        self.use_norm = use_norm
        config = tf.ConfigProto(
            device_count={'GPU': (1 if use_gpu else 0)}
        )
        config.gpu_options.allow_growth = True
        self.session = tf.Session(config=config)

gaphex

import pandas as pd
import json

!wget http://www.cs.cmu.edu/~ark/personas/data/MovieSummaries.tar.gz
!tar -xvzf MovieSummaries.tar.gz

plots_df = pd.read_csv('MovieSummaries/plot_summaries.txt', sep='\t', header=None)
meta_df = pd.read_csv('MovieSummaries/movie.metadata.tsv', sep='\t', header=None)

plot = {}

gaphex

import pandas as pd
import json

!wget http://www.cs.cmu.edu/~ark/personas/data/MovieSummaries.tar.gz
!tar -xvzf MovieSummaries.tar.gz

plots_df = pd.read_csv('MovieSummaries/plot_summaries.txt', sep='\t', header=None)
meta_df = pd.read_csv('MovieSummaries/movie.metadata.tsv', sep='\t', header=None)

plot = {}

gaphex

import pandas as pd
import json

!wget http://www.cs.cmu.edu/~ark/personas/data/MovieSummaries.tar.gz
!tar -xvzf MovieSummaries.tar.gz

plots_df = pd.read_csv('MovieSummaries/plot_summaries.txt', sep='\t', header=None)
meta_df = pd.read_csv('MovieSummaries/movie.metadata.tsv', sep='\t', header=None)

plot = {}

gaphex

X_vect = bert_vectorizer(X, verbose=True)

gaphex

def buildMovieRecommender(movie_names, vectorized_plots, top_k=10):
  retriever = L2Retriever(vectorized_plots.shape[1], use_norm=True, top_k=top_k, use_gpu=False)
  vectorized_norm = np.sum(vectorized_plots**2, axis=1).reshape((-1,1))
  
  def recommend(query):
    try:
      idx = retriever.predict(vectorized_plots, 
                              vectorized_plots[movie_names.index(query)], 
                              vectorized_norm)[0][1:]
      for i in idx:

gaphex

from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report

Xtr, Xts, Ytr, Yts = train_test_split(X, Y, random_state=34)

mlp = LogisticRegression()
mlp.fit(Xtr, Ytr)

print(classification_report(Yts, mlp.predict(Xts)))

gaphex

def build_module_fn(config_path, vocab_path, do_lower_case=True):

    def bert_module_fn(is_training):
        """Spec function for a token embedding module."""

        input_ids = tf.placeholder(shape=[None, None], dtype=tf.int32, name="input_ids")
        input_mask = tf.placeholder(shape=[None, None], dtype=tf.int32, name="input_mask")
        token_type = tf.placeholder(shape=[None, None], dtype=tf.int32, name="segment_ids")

        config = BertConfig.from_json_file(config_path)