PARSER.save(tree_path) # かかり受け解析したものをファイルに保存
print("Indexを読み込みます...")
VECTORIZER = Vectorizer(index_path, t=1, list=whitelist) # Indexの読み込み
print('Treeを読み込みます')
vectors = VECTORIZER.get_vector([tree_path + '/' + root + '.eda'],
filter=3) # ベクトルを生成
print(vectors)
print('Vectorを保存します')
VECTORIZER.save(vectors, [vector_path]) # ベクトルを保存
#-----
# いまもっているTFIDFコーパスベクトル群と、クエリベクトルtfidf_vectorsを比較
#----
print('TFIDF corpus Vectorsを読み込みます')
tfidf_corpus_vectors = VECTORIZER.load(
sorted(glob.glob(tfidf_DB_path + '/*.vector')))
print(tfidf_corpus_vectors)
print('IDF Vectorを読み込みます')
IDF_vector = VECTORIZER.load_IDF(IDF_path)
print(IDF_vector)
print('クエリをTFIDF化します...')
tfidf_vectors = vectors * IDF_vector
print(tfidf_vectors)
print('クエリのTFIDF Vectorを保存します:保存先は')
print(tfidf_vector_path)
VECTORIZER.save(tfidf_vectors, [tfidf_vector_path])
print('類似度')
if len(sys.argv) == 1:
sys.exit()
# Load Raw Data Files
df_users = pd.read_csv(get_data_file_path('users'))
df_jobs = pd.read_csv(get_raw_file_path('jobs'))
u = int(sys.argv[1]) #326
index = np.where(df_users['applicant_id'] == u)[0][0]
user_query = df_users.iloc[[index]]
print('[User Information -------------------------------]')
print(df_users[df_users['applicant_id'] == u])
vectorizer = Vectorizer.load(get_pickle_file_path('vectorizer'))
tfidf_jobs = pickle.load(open(get_pickle_file_path('tfidf'), "rb"))
tfidf_user = vectorizer.transform((user_query['text']))
cos_similarity_tfidf = list(map(lambda x: cosine_similarity(tfidf_user, x), tfidf_jobs))
def get_recommendation(top, df_all, scores):
recommendation = pd.DataFrame(columns = ['ApplicantID', 'JobID', 'title', 'job_description', 'score'])
count = 0
for i in top:
recommendation.at[count, 'ApplicantID'] = u
recommendation.at[count, 'JobID'] = df_all['Job.ID'][i]
recommendation.at[count, 'title'] = df_all['Title'][i]
recommendation.at[count, 'job_description'] = df_all['Job.Description'][i]
