def test_predictors():
y = "Survived"
df = pd.read_csv("examples/titanic.csv")
df = df[["Age", y]]
result_df = pps.predictors(df, y)
assert isinstance(result_df, pd.DataFrame)
assert not y in result_df.index
list_of_dicts = pps.predictors(df, y, output="list")
assert isinstance(list_of_dicts, list)
assert isinstance(list_of_dicts[0], dict)
def pred_power(clean_df, pred_column):
pps_df = pps.predictors(clean_df,
y=pred_column,
cross_validation=4,
random_seed=123)
# pps_df[pps_df['ppscore']>0]
return pps_df.sort_values(
by="model_score", axis=0,
ascending=True), pps_df.sort_values(by="model_score",
axis=0,
ascending=True)['x'][:5].values
def test_predictors():
y = "Survived"
df = pd.read_csv("examples/titanic.csv")
df = df[["Age", y]]
duplicate_column_names_df = pd.DataFrame()
duplicate_column_names_df["x1"] = np.random.uniform(-2, 2, 10)
duplicate_column_names_df["x2"] = np.random.uniform(-2, 2, 10)
duplicate_column_names_df["unique_column_name"] = np.random.uniform(-2, 2, 10)
duplicate_column_names_df.columns = [
"duplicate_column_name",
"duplicate_column_name",
"unique_column_name",
]
# check input types
with pytest.raises(TypeError):
numpy_array = np.random.randn(10, 10) # not a DataFrame
pps.predictors(numpy_array, y)
with pytest.raises(ValueError):
pps.predictors(df, "y_column_that_does_not_exist")
with pytest.raises(ValueError):
pps.predictors(df, y, output="invalid_output_type")
with pytest.raises(ValueError):
pps.predictors(df, y, sorted="invalid_value_for_sorted")
with pytest.raises(AssertionError):
# df shall not have duplicate column names
pps.predictors(duplicate_column_names_df, "duplicate_column_name")
# check return types
result_df = pps.predictors(df, y)
assert isinstance(result_df, pd.DataFrame)
assert not y in result_df.index
list_of_dicts = pps.predictors(df, y, output="list")
assert isinstance(list_of_dicts, list)
assert isinstance(list_of_dicts[0], dict)
def get_predictors(self) -> DataFrame:
if self.target is not None:
self.predictors = pps.predictors(
self.data, y=self.target)[['x', 'ppscore']].set_index(['x'])
return self.predictors
import pandas as pd
import seaborn as sns
import ppscore as pps
from pandas import ExcelFile
traindata = 'D://Download//traindata.xlsx'
df = pd.read_excel("D://Download//traindata.xlsx")
predictors_df = pps.predictors(df, y="label")
plot = sns.barplot(data=predictors_df, x="x", y="ppscore")
plot.set_xticklabels(plot.get_xticklabels(), rotation=90)