corrected vif function loop off by one mistake (oops)

moj-analytical-services · Oct 31, 2020 · 6a54b16 · 6a54b16
1 parent eee715f
commit 6a54b16
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/splink/diagnostics.py b/splink/diagnostics.py
@@ -62,7 +62,7 @@ def vif_gammas(inputdata, sparksession, sampleratio=1.0):
 
         # round robin computation of r_squared and vif from the available vars
         train_t = inputdata.rdd.map(
-            lambda x: [Vectors.dense(x[2:i] + x[i + 1 :]), x[i]]
+            lambda x: [Vectors.dense(x[1:i] + x[i + 1 :]), x[i]]
         ).toDF(["features", "label"])
 
         lr = LinearRegression(featuresCol="features", labelCol="label")