Rebase static files and models

@@ -45,7 +45,7 @@ if __name__ == "__main__":
                          "that you have already run eval.py onto this, such that "
                          "inference_model.* files already exist.")
     flags.DEFINE_string(
-        "input_data_pattern", "/Volumes/HDD/develop/yt8m/3/frame/test/test*.tfrecord",
+        "input_data_pattern", "/Volumes/HDD/develop/yt8m/3/frame/eval/eval*.tfrecord",
         "File glob defining the evaluation dataset in tensorflow.SequenceExample "
         "format. The SequenceExamples are expected to have an 'rgb' byte array "
         "sequence feature as well as a 'labels' int64 context feature.")

@@ -7,14 +7,20 @@ import src.pb_util as pbutil
 import src.video_recommender as recommender
 import src.video_util as videoutil
 
-# Define model paths.
+# Old model
 MODEL_PATH = "./model/inference_model/segment_inference_model"
 TAG_VECTOR_MODEL_PATH = "./model/tag_vectors.model"
 VIDEO_VECTOR_MODEL_PATH = "./model/video_vectors.model"
+VIDEO_TAGS_PATH = "./statics/kaggle_solution_40k.csv"
+
+# New model
+# MODEL_PATH = "./new_model/inference_model/segment_inference_model"
+# TAG_VECTOR_MODEL_PATH = "./new_model/tag_vectors.model"
+# VIDEO_VECTOR_MODEL_PATH = "./new_model/video_vectors.model"
+# VIDEO_TAGS_PATH = "./statics/new_kaggle_solution_40k.csv"
 
 # Define static file paths.
 SEGMENT_LABEL_PATH = "./statics/segment_label_ids.csv"
-VIDEO_TAGS_PATH = "./statics/kaggle_solution_40k.csv"
 VOCAB_PATH = "./statics/vocabulary.csv"
 
 # Define parameters.

@@ -4,7 +4,7 @@ import pandas as pd
 
 # Load files.
 nltk.download('stopwords')
-vocab = pd.read_csv('../vocabulary.csv')
+vocab = pd.read_csv('./new_statics/vocabulary.csv')
 
 # Lower corpus and Remove () from name.
 vocab['WikiDescription'] = vocab['WikiDescription'].str.lower().str.replace('[^a-zA-Z0-9]', ' ')

@@ -8,7 +8,7 @@ def recommend_videos(tags, tag_model_path, video_model_path, top_k):
 
     video_vector = np.zeros(100)
     for (tag, weight) in tags:
-        if tag in tag_vectors.index_to_key:
+        if tag in tag_vectors.vocab:
             video_vector = video_vector + (tag_vectors[tag] * float(weight))
         else:
             # Pass if tag is unknown

@@ -5,16 +5,12 @@ from gensim.models import Word2Vec
 BATCH_SIZE = 1000
 
 
-def vectorization_video():
-    print('[0.1 0.2]')
-
-
 if __name__ == '__main__':
-    tag_vectors = Word2Vec.load("tag_vectors.model").wv
+    tag_vectors = Word2Vec.load("new_model/tag_vectors.model").wv
     video_vectors = Word2Vec().wv   # Empty model
 
     # Load video recommendation tags.
-    video_tags = pd.read_csv('statics/kaggle_solution_40k.csv')
+    video_tags = pd.read_csv('statics/new_kaggle_solution_40k.csv')
 
     # Define batch variables.
     batch_video_ids = []