fix famd on unseen values

MaxHalford · Nov 17, 2024 · 26eb962 · 26eb962
1 parent e8af795
commit 26eb962
Show file tree

Hide file tree

Showing 3 changed files with 34 additions and 4 deletions.
diff --git a/prince/famd.py b/prince/famd.py
@@ -112,7 +112,7 @@ def row_coordinates(self, X):
         prop = X_cat.sum() / X_cat.sum().sum() * 2
         X_cat = X_cat.sub(X_cat.mean(axis="rows")).div(prop**0.5, axis="columns")
 
-        Z = pd.concat([X_num, X_cat], axis=1)
+        Z = pd.concat([X_num, X_cat.sparse.to_dense()], axis=1).fillna(0.0)
 
         return super().row_coordinates(Z)
 

diff --git a/tests/test_famd.py b/tests/test_famd.py
@@ -96,3 +96,33 @@ def test_col_contrib(self):
         F = load_df_from_R("famd$var$contrib")
         P = self.famd.column_contributions_
         np.testing.assert_allclose(F, P * 100)
+
+
+def test_issue_169():
+    """
+
+    https://github.com/MaxHalford/prince/issues/169
+
+    >>> import pandas as pd
+    >>> from prince import FAMD
+    >>> df = pd.DataFrame({'var1':['c', 'a', 'b','c'], 'var2':['x','y','y','z'],'var2': [0.,10.,30.4,0.]})
+
+    >>> famd = FAMD(n_components=2, random_state=42)
+    >>> famd = famd.fit(df[:3])
+
+    >>> famd.transform(df[0:3])
+    component         0         1
+    0         -1.303760 -0.658334
+    1         -0.335621  0.981047
+    2          1.639381 -0.322713
+
+    >>> famd.transform(df[0:2])
+    component         0         1
+    0         -1.000920 -0.669274
+    1         -0.092001  0.669274
+
+    >>> famd.transform(df[3:])
+    component         0             1
+    3         -0.869173 -1.215925e-16
+
+    """
diff --git a/tests/test_mca.py b/tests/test_mca.py
@@ -1,6 +1,5 @@
 from __future__ import annotations
 
-import io
 import tempfile
 
 import numpy as np
@@ -194,13 +193,14 @@ def test_type_doesnt_matter():
         np.testing.assert_allclose(outputs[i], outputs[i + 1])
 
 
-issue_161_data = '''
+issue_161_data = """
 ,category,userid,location,applicationname,browser\n
 0,Portal Login,a@b.com,"San Jose, CA, United States",A,Chrome\n
 1,Application Access,b@b.com,"San Jose, CA, United States",B,Other\n
 2,Application Access,a@b.com,"San Jose, CA, United States",C,Other\n
 3,Portal Login,c@b.com,"San Diego, CA, United States",A,Chrome\n
-'''
+"""
+
 
 def test_issue_161():
     """