shaypal5

image: python:3.8.3

# pipeline stages definitions
test: &test
  step:
    name: test
    caches:
      - pip
    script:
      - python --version

shaypal5

import os
import pytest

try:
    from.temp_env_var import TEMP_ENV_VARS, ENV_VARS_TO_SUSPEND
except ImportError:
    TEMP_ENV_VARS = {}
    ENV_VARS_TO_SUSPEND = []

shaypal5

#!/bin/bash


# --- script documentation
# recieves two arrays as input using the length prefix convention. See:
# https://stackoverflow.com/questions/43686878/pass-multiple-arrays-as-arguments-to-a-bash-script

# add mandatory packages here
# packages+=("pandas")
echo ">>> conda_envs: ${conda_envs[@]}"

shaypal5

sudo apt-get remove --purge vim vim-runtime vim-gnome vim-tiny vim-gui-common

sudo apt-get install build-essential cmake
sudo apt-get install python-dev python3-dev

#Optional: so vim can be uninstalled again via `dpkg -r vim`
sudo apt-get install checkinstall

sudo rm -rf /usr/local/share/vim /usr/bin/vim

shaypal5

import pandas as pd; import deepchecks; 
from deepchecks.datasets.classification.phishing import load_data
df = load_data(data_format='dataframe', as_train_test=False)
df.head(5)

shaypal5

from deepchecks.suites import single_dataset_integrity
integ_suite = single_dataset_integrity()
integ_suite.run(test_dataset=df)

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']

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.suites import model_evaluation
msuite = model_evaluation()
msuite.run(model=logreg, 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)