модель для актеров изменена по биграммы

app.py

@@ -19,7 +19,7 @@ input_search = st.text_input('Search')
 
 tfidf_slider = st.sidebar.slider("tf_idf_description", 0.0, 1.0, 0.9)
 tf_idf_name = st.sidebar.slider("tf_idf_name", 0.0, 1.0, 0.0083)
-tf_idf_actors = st.sidebar.slider("tf_idf_actors", 0.0, 1.0, 0.9)
+tf_idf_actors = st.sidebar.slider("tf_idf_actors", 0.0, 1.0, 0.9)*10
 bert_weight = st.sidebar.slider("bert_weight", 0.0, 1.0, 0.9)
 
 
@@ -227,10 +227,6 @@ def getnums(df,size=0,text=''):
         return reqs[text]
 
 
-
-
-
-
 if input_search:
     for i in predict_rating(input_search,tfidf_slider,tf_idf_name,tf_idf_actors,bert_weight):
         display_movie_card(movies, i )

data/books_model (2).ipynb

@@ -388,11 +388,11 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 10,
+      "execution_count": 16,
       "metadata": {},
       "outputs": [],
       "source": [
-        "vectorizer = TfidfVectorizer(ngram_range=(1, 2))\n",
+        "vectorizer = TfidfVectorizer(ngram_range=(2, 2), sublinear_tf=True)\n",
         "a=vectorizer.fit_transform(data['actors'].fillna(''))\n"
       ]
     },
@@ -459,7 +459,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 11,
+      "execution_count": 17,
       "metadata": {},
       "outputs": [],
       "source": [

data/vectorizer_actors.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afe1032cfedea73140c67f1b1480bd24ceefa0087b015aa86ed091d80517eb07
-size 19423397
+oid sha256:f91f10d57cc9977375956d315bc58d81a09b5d4433b52df38481dd5ed3614d15
+size 16325508