github/sql-server-samples
1
0
Fork 0
mirror of https://github.com/Microsoft/sql-server-samples.git synced 2025-12-08 14:58:54 +00:00
Code Issues Releases Wiki Activity

update OneHotEncoder class name

Browse Source
This commit is contained in:
Renat Bekbolatov
2022-01-11 16:43:13 -08:00
parent 98f71869e3
commit b9fc66c425
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
samples/features/sql-big-data-cluster/spark/sparkml/train_score_export_ml_models_with_spark.ipynb
+4 -4
View File
@@ -313,7 +313,7 @@
"cell_type": "code",
"source": [
"from pyspark.ml import Pipeline, PipelineModel\r\n",
"from pyspark.ml.feature import OneHotEncoderEstimator, StringIndexer, VectorAssembler\r\n",
"from pyspark.ml.feature import OneHotEncoder, StringIndexer, VectorAssembler\r\n",
"from pyspark.ml.classification import LogisticRegression\r\n",
"\r\n",
"reg = 0.1\r\n",
@@ -335,7 +335,7 @@
" \r\n",
" tmpCol = \"-\".join([key, \"tmp\"])\r\n",
" si_xvars.append(StringIndexer(inputCol=key, outputCol=tmpCol, handleInvalid=\"skip\")) #, handleInvalid=\"keep\"\r\n",
" ohe_xvars.append(OneHotEncoderEstimator(inputCols=[tmpCol], outputCols=[featureCol]))\r\n",
" ohe_xvars.append(OneHotEncoder(inputCols=[tmpCol], outputCols=[featureCol]))\r\n",
" else:\r\n",
" featureCols.append(key)\r\n",
"\r\n",
@@ -378,7 +378,7 @@
},
{
"name": "stdout",
"text": "Using LogisticRegression model with Regularization Rate of 0.1.\nPipeline Created\nModel Trained\nModel is PipelineModel_dd10dea16fcc\nModel Stages [StringIndexer_a72809f2344f, OneHotEncoderEstimator_bff5847e2bae, StringIndexer_e62df3c26c82, VectorAssembler_e84f4c37608c, LogisticRegressionModel: uid = LogisticRegression_96385e6ff190, numClasses = 2, numFeatures = 17]",
"text": "Using LogisticRegression model with Regularization Rate of 0.1.\nPipeline Created\nModel Trained\nModel is PipelineModel_dd10dea16fcc\nModel Stages [StringIndexer_a72809f2344f, OneHotEncoder_bff5847e2bae, StringIndexer_e62df3c26c82, VectorAssembler_e84f4c37608c, LogisticRegressionModel: uid = LogisticRegression_96385e6ff190, numClasses = 2, numFeatures = 17]",
"output_type": "stream"
}
],
@@ -550,4 +550,4 @@
"execution_count": 27
}
]
}
}