def random_forest(df, columns, input_col, **kwargs):
"""
Runs a random forest classifier for input DataFrame.
:param df: Pyspark dataframe to analyze.
:param columns: List of columns to select for prediction.
:param input_col: Column to predict.
:return: DataFrame with random forest and prediction run.
"""
columns = parse_columns(df, columns)
data = df.select(columns)
feats = data.columns
feats.remove(input_col)
df = string_to_index(df, input_cols=input_col)
df = vector_assembler(df, input_cols=feats, output_col="features")
model = RandomForestClassifier(**kwargs)
df.table()
df = df.cols.rename(name_col(input_col, "index_to_string"), "label")
rf_model = model.fit(df)
df_model = rf_model.transform(df)
return df_model, rf_model
def gbt(df, columns, input_col, **kwargs):
"""
Runs a gradient boosting tree classifier for input DataFrame.
:param df: Pyspark dataframe to analyze.
:param columns: List of columns to select for prediction.
:param input_col: Column to predict.
:return: DataFrame with gradient boosting tree and prediction run.
"""
if not is_dataframe(df):
raise TypeError("Spark dataframe expected")
columns = parse_columns(df, columns)
if not is_str(input_col):
raise TypeError("Error, input column must be a string")
data = df.select(columns)
feats = data.columns
feats.remove(input_col)
df = string_to_index(df, input_cols=input_col)
df = vector_assembler(df, input_cols=feats, output_col="features")
model = GBTClassifier(**kwargs)
df = df.cols.rename(name_col(input_col, "index_to_string"), "label")
gbt_model = model.fit(df)
df_model = gbt_model.transform(df)
return df_model, gbt_model
def decision_tree(df, columns, input_col, **kargs):
"""
Runs a decision tree classifier for input DataFrame.
:param df: Pyspark dataframe to analyze.
:param columns: List of columns to select for prediction.
:param input_col: Column to predict.
:return: DataFrame with decision tree and prediction run.
"""
if not is_dataframe(df):
raise TypeError("Spark dataframe expected")
columns = parse_columns(df, columns)
if not is_str(input_col):
raise TypeError("Error, input column must be a string")
data = df.select(columns)
feats = data.columns
feats.remove(input_col)
df = string_to_index(df, input_cols=input_col)
df = vector_assembler(df, input_cols=feats)
model = DecisionTreeClassifier(**kargs)
df = df.cols.rename(name_col(input_col, "index"), "label")
dt_model = model.fit(df)
df_model = dt_model.transform(df)
return df_model, dt_model
def random_forest(df, columns, input_col, **kargs):
"""
Runs a random forest classifier for input DataFrame.
:param df: Pyspark dataframe to analyze.
:param columns: List of columns to select for prediction.
:param input_col: Column to predict.
:return: DataFrame with random forest and prediction run.
"""
if not is_dataframe(df):
raise TypeError("Spark dataframe expected")
columns = parse_columns(df, columns)
assert isinstance(input_col,
str), "Error, input column must be a string"
data = df.select(columns)
feats = data.columns
feats.remove(input_col)
df = string_to_index(df, input_cols=input_col)
df = vector_assembler(df, input_cols=feats)
model = RandomForestClassifier(**kargs)
df = df.cols.rename([(input_col + "_index", "label")])
rf_model = model.fit(df)
df_model = rf_model.transform(df)
return df_model, rf_model
def h2o_xgboost(df, label, columns, **kargs):
H2OContext.getOrCreate(Spark.instance.spark)
df_sti = string_to_index(df, input_cols=label)
df_va = vector_assembler(df_sti, input_cols=columns)
h2o_xgboost = H2OXGBoost(convertUnknownCategoricalLevelsToNa=True,
featuresCols=columns,
labelCol=label,
**kargs)
model = h2o_xgboost.fit(df_va)
df_raw = model.transform(df_va)
df_pred = df_raw.withColumn("prediction", when(df_raw.prediction_output["p1"] > 0.5, 1.0).otherwise(0.0))
return df_pred, model
def h2o_gbm(df, label, columns, **kargs):
H2OContext.getOrCreate(Spark.instance.spark)
df_sti = string_to_index(df, input_cols=label)
df_va = vector_assembler(df_sti, input_cols=columns)
h2o_gbm = H2OGBM(ratio=0.8,
seed=1,
featuresCols=columns,
labelCol=label,
**kargs)
model = h2o_gbm.fit(df_va)
df_raw = model.transform(df_va)
df_pred = df_raw.withColumn("prediction", when(df_raw.prediction_output["p1"] > 0.5, 1.0).otherwise(0.0))
return df_pred, model
def h2o_automl(df, label, columns, **kargs):
H2OContext.getOrCreate(Spark.instance.spark)
df_sti = string_to_index(df, input_cols=label)
df_va = vector_assembler(df_sti, input_cols=columns)
automl = H2OAutoML(convertUnknownCategoricalLevelsToNa=True,
maxRuntimeSecs=60, # 1 minutes
seed=1,
maxModels=3,
labelCol=label + "_index",
**kargs)
model = automl.fit(df_va)
df_raw = model.transform(df_va)
df_pred = df_raw.withColumn("prediction", when(df_raw.prediction_output["value"] > 0.5, 1.0).otherwise(0.0))
return df_pred, model
def h2o_deeplearning(df, label, columns, **kargs):
H2OContext.getOrCreate(Spark.instance.spark)
df_sti = string_to_index(df, input_cols=label)
df_va = vector_assembler(df_sti, input_cols=columns)
h2o_deeplearning = H2ODeepLearning(epochs=10,
seed=1,
l1=0.001,
l2=0.0,
hidden=[200, 200],
featuresCols=columns,
labelCol=label,
**kargs)
model = h2o_deeplearning.fit(df_va)
df_raw = model.transform(df_va)
df_pred = df_raw.withColumn("prediction", when(df_raw.prediction_output["p1"] > 0.5, 1.0).otherwise(0.0))
return df_pred, model
def test_string_to_index_kargs():
df = op.spark.createDataFrame([(0, "a"), (1, "b"), (2, "c"), (3, "a"),
(4, "a"), (5, "c")], ["id", "category"])
df_indexed = fe.string_to_index(df,
"category",
stringOrderType="frequencyAsc")
assert_spark_df(df_indexed)
expected_collect = op.sc.parallelize([
Row(id=0, category='a', category_index=2.0),
Row(id=1, category='b', category_index=0.0),
Row(id=2, category='c', category_index=1.0),
Row(id=3, category='a', category_index=2.0),
Row(id=4, category='a', category_index=2.0),
Row(id=5, category='c', category_index=1.0)
]).toDF()
assert_equal(
df_indexed.select("category", "category_index", "id").collect(),
expected_collect.collect())
