# MAGIC to evaluate the predictions. The following statistics are calculated for
# MAGIC regression models to evaluate:
# MAGIC * Mean squared error
# MAGIC * Root mean squared error
# MAGIC * R^2
# MAGIC * Mean absolute error
# MAGIC
# MAGIC Use the `ComputeModelStatistics` API to compute basic statistics for
# MAGIC the Poisson and the Random Forest models.
# COMMAND ----------
from mmlspark.train import ComputeModelStatistics
poissonMetrics = ComputeModelStatistics().transform(poissonPrediction)
print("Poisson Metrics")
poissonMetrics.toPandas()
# COMMAND ----------
randomForestMetrics = ComputeModelStatistics().transform(
randomForestPrediction)
print("Random Forest Metrics")
randomForestMetrics.toPandas()
# COMMAND ----------
# MAGIC %md We can also compute per instance statistics for `poissonPrediction`:
# COMMAND ----------
from mmlspark.train import ComputePerInstanceStatistics
# COMMAND ----------
# MAGIC %md Score the regressor on the test data.
# COMMAND ----------
scoredData = model.transform(testCat)
scoredData.limit(10).toPandas()
# COMMAND ----------
# MAGIC %md Compute model metrics against the entire scored dataset
# COMMAND ----------
from mmlspark.train import ComputeModelStatistics
metrics = ComputeModelStatistics().transform(scoredData)
metrics.toPandas()
# COMMAND ----------
# MAGIC %md Finally, compute and show statistics on individual predictions in the test
# MAGIC dataset, demonstrating the usage of `ComputePerInstanceStatistics`
# COMMAND ----------
from mmlspark.train import ComputePerInstanceStatistics
evalPerInstance = ComputePerInstanceStatistics().transform(scoredData)
evalPerInstance.select("ArrDelay", "Scores", "L1_loss", "L2_loss") \
.limit(10).toPandas()
# COMMAND ----------
# MAGIC %md We evaluate the prediction result by using `mmlspark.train.ComputeModelStatistics` which returns four metrics:
# MAGIC * [MSE (Mean Squared Error)](https://en.wikipedia.org/wiki/Mean_squared_error)
# MAGIC * [RMSE (Root Mean Squared Error)](https://en.wikipedia.org/wiki/Root-mean-square_deviation) = sqrt(MSE)
# MAGIC * [R quared](https://en.wikipedia.org/wiki/Coefficient_of_determination)
# MAGIC * [MAE (Mean Absolute Error)](https://en.wikipedia.org/wiki/Mean_absolute_error)
# COMMAND ----------
metrics = ComputeModelStatistics(
evaluationMetric='regression', labelCol='target',
scoresCol='prediction').transform(lr_predictions)
results = metrics.toPandas()
results.insert(0, 'model', ['Spark MLlib - Linear Regression'])
display(results)
# COMMAND ----------
# MAGIC %md ## Vowpal Wabbit
# COMMAND ----------
# MAGIC %md Perform VW-style feature hashing. Many types (numbers, string, bool, map of string to (number, string)) are supported.
# COMMAND ----------
vw_featurizer = VowpalWabbitFeaturizer(
inputCols=feature_cols,