shaypal5

>>> mp = MyPipelineAndModel(
      savings_max_val=101,
      drop_gender=False,
      standardize=True,
      ohencode_country=True,
      savings_bin_val=1,
      pca_threshold=25,
      fit_intercept=True)
>>> mp
<PdPipeline -> LogisticRegression>

shaypal5

from typing import Optional
import pdpipe as pdp
from pdpipe import df
from sklearn.linear_model import LogisticRegression
from pdpipe.skintegrate import PdPipelineAndSklearnEstimator

class MyPipelineAndModel(PdPipelineAndSklearnEstimator):
    
    def __init__(
        self,

shaypal5

>>> df = pd.DataFrame(
...   [[23, 'Jo', 45], [19, 'Bo', 72], [15, 'Di', 12], [5, 'Jo', 0]],
...   columns=['age', 'name', 'salary'])
>>> df
   age name  salary
0   23   Jo      45
1   19   Bo      72
2   15   Di      12
3    5   Jo       0
>>> pipeline = pdp.DropDuplicates('name').Bin({'salary': [0, 20, 50]}) \

shaypal5

from typing import Tuple, Optional
import numpy as np
import pandas as pd


def train_val_split(
    training_df: pd.DataFrame,
    val_ratio: float,
) -> Tuple[pd.DataFrame, pd.DataFrame]:
    """Splits the input training dataset into train/val set.

shaypal5

>>> df = pd.DataFrame(
        data=[[4, 165, 'USA'], [2, 180, 'UK'], [2, 170, 'Greece']],
        index=['Dana', 'Jane', 'Nick'],
        columns=['Medals', 'Height', 'Born']
    )
>>> df
      Medals  Height    Born
Dana       4     165     USA
Jane       2     180      UK
Nick       2     170  Greece

shaypal5

from sklearn.ensemble import GradientBoostingClassifier
model = GradientBoostingClassifier(n_estimators=250, random_state=SEED, max_depth=20, subsample=0.8 , loss='exponential')
model.fit(train_X, train_y)
msuite.run(model=model, train_dataset=ds_train, test_dataset=ds_test)

shaypal5

from sklearn.tree import DecisionTreeClassifier
model = DecisionTreeClassifier(criterion='entropy', splitter='random', random_state=SEED)
model.fit(train_X, train_y)
msuite.run(model=model, train_dataset=ds_train, test_dataset=ds_test)

shaypal5

from deepchecks.suites import model_evaluation
msuite = model_evaluation()
msuite.run(model=logreg, train_dataset=ds_train, test_dataset=ds_test)

shaypal5

from deepchecks.suites import train_test_validation
vsuite = train_test_validation()
ds_train = deepchecks.Dataset(df=train_X, label=train_y, set_datetime_from_dataframe_index=True, cat_features=[])
ds_test = deepchecks.Dataset(df=test_X, label=test_y, set_datetime_from_dataframe_index=True, cat_features=[])
vsuite.run(model=logreg, train_dataset=ds_train, test_dataset=ds_test)

shaypal5

from deepchecks.datasets.classification.phishing import get_url_preprocessor
pipeline = get_url_preprocessor()
train_df = pipeline.fit_transform(raw_train_df)
train_X = train_df.drop('target', axis=1)
train_y = train_df['target']
test_df = pipeline.transform(raw_test_df)
test_X = test_df.drop('target', axis=1)
test_y = test_df['target']