api

engine.py

@@ -2,64 +2,72 @@ from simpful import *
 
 FS = FuzzySystem()
 
-# Define fuzzy sets for the variable # Define fuzzy sets for the variable 
+# Define fuzzy sets for the variable
 # RELEASE_YEAR
 release_year_newer = TriangleFuzzySet(-68, -68, 0, term="newer")
 release_year_similar = TriangleFuzzySet(-68, 0, 68, term="similar")
 release_year_older = TriangleFuzzySet(0, 68, 68, term="older")
 
-FS.add_linguistic_variable("RELEASE_YEAR", LinguisticVariable( [release_year_newer, release_year_similar, release_year_older], universe_of_discourse=[-136, 136] ))
+FS.add_linguistic_variable("RELEASE_YEAR",
+                           LinguisticVariable([release_year_newer, release_year_similar, release_year_older],
+                                              universe_of_discourse=[-136, 136]))
 
 # RUNTIME
 runtime_shorter = TriangleFuzzySet(-238, -238, 0, term="shorter")
 runtime_similar = TriangleFuzzySet(-238, 0, 238, term="similar")
 runtime_longer = TriangleFuzzySet(0, 238, 238, term="longer")
 
-FS.add_linguistic_variable("RUNTIME", LinguisticVariable( [runtime_shorter, runtime_similar, runtime_longer], universe_of_discourse=[-476, 476] ))
+FS.add_linguistic_variable("RUNTIME", LinguisticVariable([runtime_shorter, runtime_similar, runtime_longer],
+                                                         universe_of_discourse=[-476, 476]))
 
 # SEASONS
 seasons_less = TriangleFuzzySet(-42, -42, 0, term="less")
 seasons_similar = TriangleFuzzySet(-42, 0, 42, term="similar")
 seasons_more = TriangleFuzzySet(0, 42, 42, term="more")
 
-FS.add_linguistic_variable("SEASONS", LinguisticVariable( [seasons_less, seasons_similar, seasons_more], universe_of_discourse=[-84, 84] ))
+FS.add_linguistic_variable("SEASONS", LinguisticVariable([seasons_less, seasons_similar, seasons_more],
+                                                         universe_of_discourse=[-84, 84]))
 
 # GENRES
 genres_different = TriangleFuzzySet(-100, -100, 0, term="different")
 genres_similar = TriangleFuzzySet(-100, 0, 100, term="similar")
 genres_same = TriangleFuzzySet(0, 100, 100, term="same")
 
-FS.add_linguistic_variable("GENRES", LinguisticVariable( [genres_different, genres_similar, genres_same], universe_of_discourse=[-200, 200] ))
+FS.add_linguistic_variable("GENRES", LinguisticVariable([genres_different, genres_similar, genres_same],
+                                                        universe_of_discourse=[-200, 200]))
 
 # EMOTIONS
 emotions_different = TriangleFuzzySet(-4, -4, 0, term="different")
 emotions_similar = TriangleFuzzySet(-4, 0, 4, term="similar")
 emotions_same = TriangleFuzzySet(0, 4, 4, term="same")
 
-FS.add_linguistic_variable("EMOTIONS", LinguisticVariable( [emotions_different, emotions_similar, emotions_same], universe_of_discourse=[-8, 8] ))
+FS.add_linguistic_variable("EMOTIONS", LinguisticVariable([emotions_different, emotions_similar, emotions_same],
+                                                          universe_of_discourse=[-8, 8]))
 
-# RECOMENDATION
+# RECOMMENDATION
-low_recomendation = TriangleFuzzySet(0, 0, 50, term="low_recomendation")
+low_recommendation = TriangleFuzzySet(0, 0, 50, term="low_recommendation")
-medium_recomendation = TriangleFuzzySet(0, 50, 100, term="medium_recomendation")
+medium_recommendation = TriangleFuzzySet(0, 50, 100, term="medium_recommendation")
-high_recomendation = TriangleFuzzySet(0, 100, 100, term="high_recomendation")
+high_recommendation = TriangleFuzzySet(0, 100, 100, term="high_recommendation")
-FS.add_linguistic_variable("RECOMENDATION", LinguisticVariable( [low_recomendation, medium_recomendation, high_recomendation], universe_of_discourse=[0, 200] ))
+FS.add_linguistic_variable("RECOMMENDATION",
+                           LinguisticVariable([low_recommendation, medium_recommendation, high_recommendation],
+                                              universe_of_discourse=[0, 200]))
 
 # RULES
-RULE1 = "IF (RELEASE_YEAR IS older) AND (RUNTIME IS longer) AND (SEASONS IS more) THEN (RECOMENDATION IS low_recomendation)"
+RULE1 = "IF (RELEASE_YEAR IS older) AND (RUNTIME IS longer) AND (SEASONS IS more) THEN (RECOMMENDATION IS low_recommendation)"
-RULE2 = "IF (EMOTIONS IS different) AND (GENRES IS different) THEN (RECOMENDATION IS low_recomendation)"
+RULE2 = "IF (EMOTIONS IS different) AND (GENRES IS different) THEN (RECOMMENDATION IS low_recommendation)"
-RULE3 = "IF (RELEASE_YEAR IS newer) AND (RUNTIME IS similar) AND (SEASONS IS less) THEN (RECOMENDATION IS medium_recomendation)"
+RULE3 = "IF (RELEASE_YEAR IS newer) AND (RUNTIME IS similar) AND (SEASONS IS less) THEN (RECOMMENDATION IS medium_recommendation)"
-RULE4 = "IF (EMOTIONS IS similar) AND (GENRES IS similar) THEN (RECOMENDATION IS medium_recomendation)"
+RULE4 = "IF (EMOTIONS IS similar) AND (GENRES IS similar) THEN (RECOMMENDATION IS medium_recommendation)"
-RULE5 = "IF (RELEASE_YEAR IS similar) AND (RUNTIME IS similar) AND (SEASONS IS similar) AND (EMOTIONS IS same) AND (GENRES IS same) THEN (RECOMENDATION IS high_recomendation)"
+RULE5 = "IF (RELEASE_YEAR IS similar) AND (RUNTIME IS similar) AND (SEASONS IS similar) AND (EMOTIONS IS same) AND (GENRES IS same) THEN (RECOMMENDATION IS high_recommendation)"
 # Z regułami trzeba eksperymentować, można porównywać ze scorem dla sprawdzania skuteczności
 
 FS.add_rules([RULE1, RULE2, RULE3, RULE4, RULE5])
 
-FS.set_variable("RELEASE_YEAR", -12.0)
+# FS.set_variable("RELEASE_YEAR", -12.0)
-FS.set_variable("RUNTIME", -10.0)
+# FS.set_variable("RUNTIME", -10.0)
-FS.set_variable("SEASONS", -2.0)
+# FS.set_variable("SEASONS", -2.0)
-FS.set_variable("GENRES", 50.0)
+# FS.set_variable("GENRES", 50.0)
-FS.set_variable("EMOTIONS", 1.0)
+# FS.set_variable("EMOTIONS", 1.0)
+#
+# print(FS.inference(["RECOMMENDATION"]))
 
-print(FS.inference(["RECOMENDATION"]))
+# FS.produce_figure(outputfile='visualize_terms.pdf')
-
-FS.produce_figure(outputfile='visualize_terms.pdf')

main.py

@@ -0,0 +1,61 @@
+"""
+!pip install scikit-learn
+!pip install pandas
+!pip install fastapi
+!pip install "uvicorn[standard]"
+!uvicorn main:app --reload
+"""
+
+import numpy as np
+import pandas as pd
+from fastapi import FastAPI
+from scipy.spatial.distance import cosine
+from sklearn.preprocessing import MultiLabelBinarizer
+
+from engine import FS
+
+app = FastAPI()
+data = pd.DataFrame()
+
+
+@app.on_event('startup')
+async def startup_event():
+    global data
+    data = pd.read_csv('processed_data.csv', index_col='id', converters={'genres': pd.eval})
+    all_genres = data.genres.explode().unique()
+    mlb = MultiLabelBinarizer()
+    mlb.fit([all_genres])
+    data['genres'] = data['genres'].apply(lambda x: mlb.transform([x])[0])
+    data['emotions'] = data[['Happy', 'Angry', 'Surprise', 'Sad', 'Fear']].values.tolist()
+
+
+@app.get('/score/{first_id}/{second_id}')
+def rec_score(first_id: str, second_id: str):
+    try:
+        first = data.loc[first_id]
+    except KeyError:
+        return {'error': f'{first_id} is not a valid id'}
+    try:
+        second = data.loc[second_id]
+    except KeyError:
+        return {'error': f'{second_id} is not a valid id'}
+
+    year_diff = int(first['release_year'] - second['release_year'])
+    FS.set_variable('RELEASE_YEAR', year_diff)
+
+    runtime_diff = int(first['runtime'] - second['runtime'])
+    FS.set_variable('RUNTIME', runtime_diff)
+
+    if not (np.isnan(first['seasons']) or np.isnan(second['seasons'])):
+        season_diff = int(first['seasons'] - second['seasons'])
+        FS.set_variable('SEASONS', season_diff)
+    else:
+        FS.set_variable('SEASONS', 0)
+
+    genre_diff = 1 - cosine(first['genres'], second['genres'])
+    FS.set_variable('GENRES', genre_diff)
+
+    emotion_diff = 1 - cosine(first['emotions'], second['emotions'])
+    FS.set_variable('EMOTIONS', emotion_diff)
+
+    return {'score': FS.inference(['RECOMMENDATION'])}