Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Bugfix in test and data type inference code #349

Merged
merged 1 commit into from
Apr 8, 2021
Merged

Bugfix in test and data type inference code #349

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 4 additions & 12 deletions lux/executor/PandasExecutor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -422,13 +422,8 @@ def compute_data_type(self, ldf: LuxDataFrame):
elif self._is_geographical_attribute(ldf[attr]):
ldf._data_type[attr] = "geographical"
elif pd.api.types.is_float_dtype(ldf.dtypes[attr]):
# int columns gets coerced into floats if contain NaN
convertible2int = pd.api.types.is_integer_dtype(ldf[attr].convert_dtypes())
if (
convertible2int
and ldf.cardinality[attr] != len(ldf)
and (len(ldf[attr].convert_dtypes().unique() < 20))
):

if ldf.cardinality[attr] != len(ldf) and (ldf.cardinality[attr] < 20):
ldf._data_type[attr] = "nominal"
else:
ldf._data_type[attr] = "quantitative"
Expand Down Expand Up @@ -525,11 +520,8 @@ def compute_stats(self, ldf: LuxDataFrame):
else:
attribute_repr = attribute

if ldf.dtypes[attribute] != "float64" or ldf[attribute].isnull().values.any():
ldf.unique_values[attribute_repr] = list(ldf[attribute].unique())
ldf.cardinality[attribute_repr] = len(ldf.unique_values[attribute])
else:
ldf.cardinality[attribute_repr] = 999 # special value for non-numeric attribute
ldf.unique_values[attribute_repr] = list(ldf[attribute].unique())
ldf.cardinality[attribute_repr] = len(ldf.unique_values[attribute_repr])

if pd.api.types.is_float_dtype(ldf.dtypes[attribute]) or pd.api.types.is_integer_dtype(
ldf.dtypes[attribute]
Expand Down
21 changes: 12 additions & 9 deletions tests/test_interestingness.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -273,25 +273,28 @@ def test_interestingness_deviation_nan():
import numpy as np

dataset = [
{"date": "2017-08-25 09:06:11+00:00", "category": "A", "value": 25.0},
{"date": "2017-08-25 09:06:11+00:00", "category": "B", "value": 1.2},
{"date": "2017-08-25 09:06:11+00:00", "category": "C", "value": 1.3},
{"date": "2017-08-25 09:06:11+00:00", "category": "D", "value": 1.4},
{"date": "2017-08-25 09:06:11+00:00", "category": "E", "value": 1.5},
{"date": "2017-08-25 09:06:11+00:00", "category": "F", "value": 0.1},
{"date": "2017-08-25", "category": "A", "value": 25.0},
{"date": "2017-08-25", "category": "B", "value": 1.2},
{"date": "2017-08-25", "category": "C", "value": 1.3},
{"date": "2017-08-25", "category": "D", "value": 1.4},
{"date": "2017-08-25", "category": "E", "value": 1.5},
{"date": "2017-08-25", "category": "F", "value": 0.1},
{"date": np.nan, "category": "C", "value": 0.2},
{"date": np.nan, "category": "B", "value": 0.2},
{"date": np.nan, "category": "F", "value": 0.3},
{"date": np.nan, "category": "E", "value": 0.3},
{"date": np.nan, "category": "D", "value": 0.4},
{"date": np.nan, "category": "A", "value": 10.4},
{"date": "2017-07-25 15:06:11+00:00", "category": "A", "value": 15.5},
{"date": "2017-07-25 15:06:11+00:00", "category": "F", "value": 1.0},
{"date": "2017-07-25 15:06:11+00:00", "category": "B", "value": 0.1},
{"date": "2017-07-25", "category": "A", "value": 15.5},
{"date": "2017-07-25", "category": "F", "value": 1.0},
{"date": "2017-07-25", "category": "B", "value": 0.1},
]
test = pd.DataFrame(dataset)
from lux.vis.Vis import Vis

test["date"] = pd.to_datetime(test["date"], format="%Y-%M-%d")
test.set_data_type({"value": "quantitative"})

vis = Vis(["date", "value", "category=A"], test)
vis2 = Vis(["date", "value", "category=B"], test)
from lux.interestingness.interestingness import interestingness
Expand Down
6 changes: 3 additions & 3 deletions tests/test_pandas_coverage.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -257,7 +257,7 @@ def test_transform(global_var):
df["Year"] = pd.to_datetime(df["Year"], format="%Y")
new_df = df.iloc[:, 1:].groupby("Origin").transform(sum)
new_df._ipython_display_()
assert list(new_df.recommendation.keys()) == ["Correlation", "Distribution", "Occurrence"]
assert list(new_df.recommendation.keys()) == ["Occurrence"]
assert len(new_df.cardinality) == 7


Expand Down Expand Up @@ -409,7 +409,7 @@ def test_loc(global_var):
assert len(new_df.cardinality) == 6
new_df = df.loc[0:10, "Displacement":"Horsepower"]
new_df._ipython_display_()
assert list(new_df.recommendation.keys()) == ["Distribution", "Occurrence"]
assert list(new_df.recommendation.keys()) == ["Correlation", "Distribution"]
assert len(new_df.cardinality) == 2
import numpy as np

Expand Down Expand Up @@ -438,7 +438,7 @@ def test_iloc(global_var):
assert len(new_df.cardinality) == 6
new_df = df.iloc[0:11, 3:5]
new_df._ipython_display_()
assert list(new_df.recommendation.keys()) == ["Distribution", "Occurrence"]
assert list(new_df.recommendation.keys()) == ["Correlation", "Distribution"]
assert len(new_df.cardinality) == 2
import numpy as np

Expand Down