def box(columns=None, output_format="plot", output_path=None):
"""
Plot boxplot
:param columns: Columns to be printed
:param output_format:
:param output_path: path where the image is going to be saved
:return:
"""
columns = parse_columns(self, columns, filter_by_column_dtypes=PYSPARK_NUMERIC_TYPES)
check_column_numbers(columns, "*")
for col_name in columns:
stats = self.cols.boxplot(col_name)
plot_boxplot({col_name: stats}, output=output_format, path=output_path)
def scatter(columns=None, buckets=30, output_format="plot", output_path=None):
"""
Plot boxplot
:param columns: columns to be printed
:param buckets: number of buckets
:param output_format:
:param output_path: path where the image is going to be saved
:return:
"""
columns = parse_columns(self, columns, filter_by_column_dtypes=PYSPARK_NUMERIC_TYPES)
check_column_numbers(columns, "*")
data = self.cols.scatter(columns, buckets)
plot_scatterplot(data, output=output_format, path=output_path)
def hist(columns=None, buckets=10, output_format="plot", output_path=None):
"""
Plot histogram
:param columns: Columns to be printed
:param buckets: Number of buckets
:param output_format:
:param output_path: path where the image is going to be saved
:return:
"""
columns = parse_columns(self,
columns,
filter_by_column_dtypes=PYSPARK_NUMERIC_TYPES)
check_column_numbers(columns, "*")
for col_name in columns:
data = self.cols.hist(col_name, buckets)
plot_hist({col_name: data}, output=output_format, path=output_path)