def test_custom_transformer():
input_df = pd.DataFrame({
'feat1': [1, 2, 3],
'feat2': [math.e, math.e**2, math.e**3],
'feat3': [1.5, 2.5, 3.5],
'target': [1, 4, 9]
})
expected = pd.DataFrame({
'feat1': [1, 2, 3],
'feat2': [math.e, math.e**2, math.e**3],
'feat3': [1.5, 2.5, 3.5],
'target': [1.0, 2.0, 3.0]
})
expected2 = pd.DataFrame({
'feat1': [1, 4, 9],
'feat2': [math.e, math.e**2, math.e**3],
'feat3': [1.5, 2.5, 3.5],
'target': [1, 4, 9]
})
transformer_fn, data, log = custom_transformer(input_df, ["target"], sqrt)
# the transformed input df should contain the square root of the target column
assert expected.equals(data)
transformer_fn, data, log = custom_transformer(input_df, ["feat1"],
lambda x: x**2)
# the transformed input df should contain the squared value of the feat1 column
assert expected2.equals(data)
expected3 = pd.DataFrame({
'feat1': [1, 2, 3],
'feat2': [1.0, 2.0, 3.0],
'feat3': [1.5, 2.5, 3.5],
'target': [1, 4, 9]
})
expected4 = pd.DataFrame({
'feat1': [1, 2, 3],
'feat2': [math.e, math.e**2, math.e**3],
'feat3': [1.0, 2.0, 3.0],
'target': [1, 4, 9]
})
transformer_fn, data, log = custom_transformer(input_df, ["feat2"],
ln,
is_vectorized=True)
# the transformed input df should contain the square root of the target column
assert expected3.equals(data)
transformer_fn, data, log = custom_transformer(input_df, ["feat3"],
floor,
is_vectorized=True)
# the transformed input df should contain the squared value of the feat1 column
assert expected4.equals(data)
def test_custom_transformer():
input_df = pd.DataFrame({'feat1': [1, 2, 3], 'target': [1, 4, 9]})
expected = pd.DataFrame({'feat1': [1, 2, 3], 'target': [1.0, 2.0, 3.0]})
expected2 = pd.DataFrame({'feat1': [1, 4, 9], 'target': [1.0, 2.0, 3.0]})
transformer_fn, data, log = custom_transformer(input_df, ["target"], sqrt)
# the transformed input df should contain the square root of the target column
assert expected.equals(data)
transformer_fn, data, log = custom_transformer(input_df, ["feat1"],
lambda x: x**2)
# the transformed input df should contain the squared value of the feat1 column
assert expected2.equals(data)
def test_custom_transformer():
input_df = pd.DataFrame(
{
"feat1": [1, 2, 3],
"feat2": [math.e, math.e ** 2, math.e ** 3],
"feat3": [1.5, 2.5, 3.5],
"target": [1, 4, 9],
}
)
expected = pd.DataFrame(
{
"feat1": [1, 2, 3],
"feat2": [math.e, math.e ** 2, math.e ** 3],
"feat3": [1.5, 2.5, 3.5],
"target": [1.0, 2.0, 3.0],
}
)
expected2 = pd.DataFrame(
{
"feat1": [1, 4, 9],
"feat2": [math.e, math.e ** 2, math.e ** 3],
"feat3": [1.5, 2.5, 3.5],
"target": [1, 4, 9],
}
)
# the transformed input df should contain the square root of the target column
pred_fn1, data1, log = custom_transformer(input_df, ["target"], sqrt)
pred_fn2, data2, log = custom_transformer(
input_df, ["target"], sqrt, suffix="_suffix"
)
pred_fn3, data3, log = custom_transformer(
input_df, ["target"], sqrt, prefix="prefix_"
)
pred_fn4, data4, log = custom_transformer(
input_df, ["target"], sqrt, columns_mapping={"target": "target_raw"}
)
assert expected.equals(data1)
assert pd.concat(
[expected, input_df[["target"]].copy().add_suffix("_suffix")], axis=1
).equals(data2)
assert pd.concat(
[expected, input_df[["target"]].copy().add_prefix("prefix_")], axis=1
).equals(data3)
assert pd.concat(
[expected, input_df[["target"]].copy().add_suffix("_raw")], axis=1
).equals(data4)
# the transformed input df should contain the squared value of the feat1 column
pred_fn1, data1, log = custom_transformer(
input_df, ["feat1"], lambda x: x ** 2
)
pred_fn2, data2, log = custom_transformer(
input_df, ["feat1"], lambda x: x ** 2, suffix="_suffix"
)
pred_fn3, data3, log = custom_transformer(
input_df, ["feat1"], lambda x: x ** 2, prefix="prefix_"
)
pred_fn4, data4, log = custom_transformer(
input_df,
["feat1"],
lambda x: x ** 2,
columns_mapping={"feat1": "feat1_raw"},
)
assert expected2.equals(data1)
assert pd.concat(
[expected2, input_df[["feat1"]].copy().add_suffix("_suffix")], axis=1
).equals(data2)
assert pd.concat(
[expected2, input_df[["feat1"]].copy().add_prefix("prefix_")], axis=1
).equals(data3)
assert pd.concat(
[expected2, input_df[["feat1"]].copy().add_suffix("_raw")], axis=1
).equals(data4)
expected3 = pd.DataFrame(
{
"feat1": [1, 2, 3],
"feat2": [1.0, 2.0, 3.0],
"feat3": [1.5, 2.5, 3.5],
"target": [1, 4, 9],
}
)
expected4 = pd.DataFrame(
{
"feat1": [1, 2, 3],
"feat2": [math.e, math.e ** 2, math.e ** 3],
"feat3": [1.0, 2.0, 3.0],
"target": [1, 4, 9],
}
)
# the transformed input df should contain the log of the target column
pred_fn1, data1, log = custom_transformer(
input_df, ["feat2"], ln, is_vectorized=True
)
pred_fn2, data2, log = custom_transformer(
input_df, ["feat2"], ln, is_vectorized=True, suffix="_suffix"
)
pred_fn3, data3, log = custom_transformer(
input_df, ["feat2"], ln, is_vectorized=True, prefix="prefix_"
)
pred_fn4, data4, log = custom_transformer(
input_df,
["feat2"],
ln,
is_vectorized=True,
columns_mapping={"feat2": "feat2_raw"},
)
assert expected3.equals(data1)
assert pd.concat(
[expected3, input_df[["feat2"]].copy().add_suffix("_suffix")], axis=1
).equals(data2)
assert pd.concat(
[expected3, input_df[["feat2"]].copy().add_prefix("prefix_")], axis=1
).equals(data3)
assert pd.concat(
[expected3, input_df[["feat2"]].copy().add_suffix("_raw")], axis=1
).equals(data4)
# the transformed input df should contain the floor value of the feat1 column
pred_fn1, data1, log = custom_transformer(
input_df, ["feat3"], floor, is_vectorized=True
)
pred_fn2, data2, log = custom_transformer(
input_df, ["feat3"], floor, is_vectorized=True, suffix="_suffix"
)
pred_fn3, data3, log = custom_transformer(
input_df, ["feat3"], floor, is_vectorized=True, prefix="prefix_"
)
pred_fn4, data4, log = custom_transformer(
input_df,
["feat3"],
floor,
is_vectorized=True,
columns_mapping={"feat3": "feat3_raw"},
)
assert expected4.equals(data1)
assert pd.concat(
[expected4, input_df[["feat3"]].copy().add_suffix("_suffix")], axis=1
).equals(data2)
assert pd.concat(
[expected4, input_df[["feat3"]].copy().add_prefix("prefix_")], axis=1
).equals(data3)
assert pd.concat(
[expected4, input_df[["feat3"]].copy().add_suffix("_raw")], axis=1
).equals(data4)