Update run.py

run.py

 from rdflib import Graph, URIRef
+from sklearn.ensemble import RandomForestClassifier
+
 from pykeen_embeddings import generate_and_save_embeddings, load_embeddings_from_file
+import pandas as pd
+import numpy as np
+from sklearn.model_selection import train_test_split
+from ml_utils import balance_data
+from sklearn.linear_model import LogisticRegression
+from sklearn.metrics import f1_score, precision_score, recall_score
 
 def read(path, format):
     """
@@ -27,17 +35,50 @@ def extract_resources(g: Graph, lp: int):
     included_res = []
     excluded_res = []
     for i, obj in enumerate(g.objects(u, include_res)):
-        included_res.append(obj)
+        included_res.append(str(obj))
 
     for i, obj in enumerate(g.objects(u, exclude_res)):
-        excluded_res.append(obj)
+        excluded_res.append(str(obj))
 
     return included_res, excluded_res
 
 
-g1 = read(path='data/kg-mini-project-train.ttl', format='turtle')
-g2 = read(path='data/carcinogenesis.owl', format='application/rdf+xml')
 
-generate_and_save_embeddings(g2, "data/carcinogenesis.tsv", "data/embeddings_carcinogenesis.tsv")
-#for lp in range(1, 26):
-#    print(extract_resources(g1, lp))
+#g2 = read(path='data/carcinogenesis.owl', format='application/rdf+xml')
+#generate_and_save_embeddings(g2, "data/carcinogenesis.tsv", "data/embeddings_carcinogenesis.tsv")
+
+def generate_features(path="data/embeddings_carcinogenesis.tsv", lp=1):
+    g1 = read(path='data/kg-mini-project-train.ttl', format='turtle')
+    included_res, excluded_res = extract_resources(g1, lp=lp)
+
+    df = pd.read_csv(path, delimiter='\t', names=['name', 'X'])
+    X = df['X'].to_list()
+    new_X = []
+    for row in X:
+        new_X.append(np.fromstring(row[1:-1], sep=','))
+    df = pd.concat([df['name'], pd.DataFrame(new_X)], axis=1)
+
+    df.loc[df['name'].isin(included_res), 'y'] = 1
+    df.loc[df['name'].isin(excluded_res), 'y'] = 0
+    df = df.dropna()
+    return df.iloc[:, 1:-1], df['y']
+
+
+for lp in range(8, 25):
+    X, y = generate_features(lp=lp)
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
+
+    X_train, y_train = balance_data(X_train, y_train, random_state=42)
+
+    clf = RandomForestClassifier(random_state=42).fit(X_train, y_train)
+    prediction = clf.predict(X_test)
+    for a, b in zip(prediction, y_test):
+        if a != b:
+            print(a,b)
+    print("F1:", f1_score(y_test, prediction))
+    print("precision:", precision_score(y_test, prediction))
+    print("recall:", recall_score(y_test, prediction))
+
+    break
+
+