def test_foreshadow_serialization_adults_small_classification_override():
from foreshadow.foreshadow import Foreshadow
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
np.random.seed(1337)
data_path = get_file_path("data", "adult_small.csv")
adult = pd.read_csv(data_path)
X_df = adult.loc[:, "age":"workclass"]
y_df = adult.loc[:, "class"]
X_train, X_test, y_train, y_test = train_test_split(X_df,
y_df,
test_size=0.2)
shadow = Foreshadow(estimator=LogisticRegression(),
problem_type=ProblemType.CLASSIFICATION)
shadow.fit(X_train, y_train)
score1 = shadow.score(X_test, y_test)
from foreshadow.intents import IntentType
shadow.override_intent("age", IntentType.CATEGORICAL)
shadow.override_intent("workclass", IntentType.CATEGORICAL)
shadow.fit(X_train, y_train)
assert shadow.get_intent("age") == IntentType.CATEGORICAL
assert shadow.get_intent("workclass") == IntentType.CATEGORICAL
score2 = shadow.score(X_test, y_test)
print(score1, score2)
def test_foreshadow_titanic(tmpdir):
import pandas as pd
train_data = pd.read_csv(get_file_path("data", "titanic-train.csv"))
X_train_df = train_data.loc[:, "Pclass":"Embarked"]
y_train_df = train_data.loc[:, "Survived"]
X_train_df = X_train_df.drop(columns=["SibSp", "Parch", "Cabin"])
X_train, X_test, y_train, y_test = train_test_split(X_train_df,
y_train_df,
test_size=0.2,
random_state=42)
from foreshadow.estimators import AutoEstimator
estimator = AutoEstimator(
problem_type=ProblemType.CLASSIFICATION,
auto="tpot",
estimator_kwargs={
"max_time_mins": 1,
"random_state": 42
},
)
shadow = Foreshadow(estimator=estimator,
problem_type=ProblemType.CLASSIFICATION)
shadow.override_intent(column_name="Name", intent=IntentType.TEXT)
shadow.fit(X_train, y_train)
score = shadow.score(X_test, y_test)
print(score)
