Added a function for simple imputation

Fabian-RY · Feb 27, 2020 · f71261d · f71261d
1 parent 23dad08
commit f71261d
Showing 1 changed file with 7 additions and 0 deletions.
diff --git a/clustering_with_pca.py b/clustering_with_pca.py
@@ -9,6 +9,13 @@
         0: KMeans,
         1: AgglomerativeClustering
         }
+#IMPUTATION OF MISSING VALUES (missing values must be np.nan)
+pandas.options.mode.use_inf_as_na = True #infinite values are considered missing
+
+def impute_values(data):
+    imp = SimpleImputer(strategy = most_frequent)
+    imp.fit(data)
+    return pd.DataFrame(imp.transform(data))
 
 #Clustering