def test_check_series(self):
data = pd.DataFrame(
data=dict(a=[1.2, 2, 3], b=[2, 3, 4], c=[1, 2, 3], d=[2, 2, 2]))
norm = MinMaxScaler() << "a"
normalized1 = norm.fit_transform(data)
normalized2 = norm.fit_transform(data['a'])
assert_array_equal(normalized1['a'].values, normalized2['a'].values)
def test_minmaxscaler_float_order_noint(self):
in_df = pandas.DataFrame(data=OrderedDict(xpetal=[-1.1, -2.2, -3.3],
ipetal=[1.0, 2.0, 3.0]))
normed = MinMaxScaler() << ['xpetal', 'ipetal']
pipeline = Pipeline([normed])
out_df = pipeline.fit_transform(in_df, verbose=0)
assert_equal(out_df.shape, (3, 2))
assert_equal(list(out_df.columns), list(in_df.columns))
def test_minmaxscaler_int(self):
in_df = pandas.DataFrame(
data=dict(xpetal=[-1, -2, -3], ipetal=[1, 2, 3]))
normed = MinMaxScaler() << ['xpetal', 'ipetal']
pipeline = Pipeline([normed])
out_df = pipeline.fit_transform(in_df, verbose=0)
assert_equal(out_df.shape, (3, 2))
if out_df.loc[2, 'xpetal'] != -1:
raise Exception("Unexpected:\n" + str(out_df))
assert_equal(out_df.loc[2, 'ipetal'], 1)
def test_fit_transform(self):
import azureml.dataprep as dprep
path = get_dataset('infert').as_filepath()
dflow = dprep.auto_read_file(path=path)
dprep_data = DprepDataStream(dflow)
file_data = FileDataStream.read_csv(path)
xf = MinMaxScaler(columns={'in': 'induced', 'sp': 'spontaneous'})
pipe = Pipeline([xf])
transformed_data = pipe.fit_transform(file_data)
transformed_data1 = pipe.fit_transform(dprep_data)
assert_array_equal(transformed_data.columns, transformed_data1.columns)
assert_2d_array_equal(transformed_data.values,
transformed_data1.values)
def transform_data():
xf = MinMaxScaler(columns={'in': 'induced', 'sp': 'spontaneous'})
pipe = Pipeline([xf])
transformed_data = pipe.fit_transform(data, as_binary_data_stream=True)
transformed_data_df = pipe.fit_transform(data)
return transformed_data, transformed_data_df
# Generate the train and test data
np.random.seed(0)
x = np.arange(100, step=0.1)
y = x * 10 + (np.random.standard_normal(len(x)) * 10)
train_data = {'c1': x, 'c2': y}
train_df = pd.DataFrame(train_data).astype({
'c1': np.float32,
'c2': np.float32
})
test_data = {'c1': [2.5, 30.5], 'c2': [1, 1]}
test_df = pd.DataFrame(test_data).astype({'c1': np.float32, 'c2': np.float32})
# Fit a MinMaxScaler Pipeline
r1 = Pipeline([MinMaxScaler()])
r1.fit(train_df)
# Export the pipeline to ONNX
onnx_path = get_tmp_file('.onnx')
r1.export_to_onnx(onnx_path, 'com.microsoft.ml', onnx_version='Stable')
# Perform the transform using the standard ML.Net backend
result_standard = r1.transform(test_df)
print(result_standard)
# c1 c2
# 0 0.025025 0.000998
# 1 0.305305 0.000998
# Perform the transform using the ONNX backend.
# Note, the extra columns and column name differences
from nimbusml import FileDataStream
from nimbusml.datasets import get_dataset
from nimbusml.preprocessing.normalization import MinMaxScaler
# data input (as a FileDataStream)
path = get_dataset('infert').as_filepath()
data = FileDataStream.read_csv(
path, sep=',', numeric_dtype=numpy.float32) # Error with integer input
print(data.head())
# age case education induced parity pooled.stratum row_num ...
# 0 26.0 1.0 0-5yrs 1.0 6.0 3.0 1.0 ...
# 1 42.0 1.0 0-5yrs 1.0 1.0 1.0 2.0 ...
# 2 39.0 1.0 0-5yrs 2.0 6.0 4.0 3.0 ...
# 3 34.0 1.0 0-5yrs 2.0 4.0 2.0 4.0 ...
# 4 35.0 1.0 6-11yrs 1.0 3.0 32.0 5.0 ...
# transform usage
xf = MinMaxScaler(columns={'in': 'induced', 'sp': 'spontaneous'})
# fit and transform
features = xf.fit_transform(data)
# print features
print(features.head())
# age case education in ... pooled.stratum row_num sp ...
# 0 26.0 1.0 0-5yrs 0.5 ... 3.0 1.0 1.0 ...
# 1 42.0 1.0 0-5yrs 0.5 ... 1.0 2.0 0.0 ...
# 2 39.0 1.0 0-5yrs 1.0 ... 4.0 3.0 0.0 ...
# 3 34.0 1.0 0-5yrs 1.0 ... 2.0 4.0 0.0 ...
# 4 35.0 1.0 6-11yrs 0.5 ... 32.0 5.0 0.5 ...
###############################################################################
# MinMaxScaler
import pandas as pd
from nimbusml.preprocessing.normalization import MinMaxScaler
in_df = pd.DataFrame(
data=dict(Sepal_Length=[2.5, 1, 2.1, 1.0],
Sepal_Width=[.75, .9, .8, .76],
Petal_Length=[0, 2.5, 2.6, 2.4],
Species=["setosa", "viginica", "setosa", 'versicolor']))
# generate two new Columns - Petal_Normed and Sepal_Normed
normed = MinMaxScaler() << {
'Petal_Normed': 'Petal_Length',
'Sepal_Normed': 'Sepal_Width'
}
out_df = normed.fit_transform(in_df)
print('MinMaxScaler\n', (out_df))