glemaitre

['/home/glemaitre/Documents/data/cycling/user_3/2015/2015-01-03-10-28-33.fit',
 '/home/glemaitre/Documents/data/cycling/user_3/2015/2015-01-09-18-14-34.fit',
 '/home/glemaitre/Documents/data/cycling/user_3/2015/2015-01-16-18-20-45.fit',
 '/home/glemaitre/Documents/data/cycling/user_3/2015/2015-01-22-17-58-25.fit',
 '/home/glemaitre/Documents/data/cycling/user_3/2015/2015-01-23-17-36-40.fit',
 '/home/glemaitre/Documents/data/cycling/user_3/2015/2015-01-30-18-03-10.fit',
 '/home/glemaitre/Documents/data/cycling/user_3/2015/2015-02-01-17-14-54.fit',
 '/home/glemaitre/Documents/data/cycling/user_3/2015/2015-02-06-18-22-13.fit',
 '/home/glemaitre/Documents/data/cycling/user_3/2015/2015-02-13-18-21-15.fit',
 '/home/glemaitre/Documents/data/cycling/user_3/2015/2015-02-14-09-05-54.fit',

glemaitre

import os
import pandas as pd
import numpy as np

from sklearn.ensemble import make_stack_layer
from sklearn.preprocessing import FunctionTransformer
from sklearn.experimental import make_column_transformer
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.preprocessing import CategoricalEncoder

glemaitre

from sklearn.datasets import load_diabetes
from sklearn.compose import TransformedTargetRegressor
from sklearn.model_selection import GridSearchCV
from sklearn.ensemble import RandomForestRegressor
from sklearn.linear_model import LinearRegression

X, y = load_diabetes(return_X_y=True)
ttr = TransformedTargetRegressor()

grid = [{'regressor': [RandomForestRegressor()], 'regressor__n_estimators': [10, 20]},

glemaitre

In [16]: df = pd.DataFrame({'A': [1, 2, 1, 2, 1, 2, 3, 3]})                                                                                                                 

In [17]: df2 = df[df['A'].isin([1, 2])]                                                                                                                                     

In [18]: df2.loc[df2['A'] == 1, 'A'] = 4                                                                                                                                    
/home/glemaitre/miniconda3/lib/python3.7/site-packages/pandas/core/indexing.py:189: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
  self._setitem_with_indexer(indexer, value)

glemaitre

import asyncio
import random
import time
from concurrent.futures import ProcessPoolExecutor


def simulator_submission():
    """Give ``None`` or a submission id."""
    return random.choice([random.randint(0, 1000), None])

glemaitre

import cv2
import matplotlib.pyplot as plt
from matplotlib.animation import FuncAnimation


def grab_frame(cap):
    _, frame = cap.read()
    return cv2.cvtColor(frame,cv2.COLOR_BGR2RGB)

glemaitre

# %%
from sklearn.datasets import make_classification
from sklearn.model_selection import StratifiedShuffleSplit
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import make_pipeline
from sklearn.model_selection import cross_validate

RANDOM_SEED = 2

glemaitre

In [1]: import numpy as np                                                                                                                                                  

In [2]: X = ["One", "string"]                                                                                                                                               

In [3]: X                                                                                                                                                                   
Out[3]: ['One', 'string']

In [4]: X[0]                                                                                                                                                                
Out[4]: 'One'

glemaitre

@pytest.mark.parametrize("name, Tree", REG_TREES.items())
@pytest.mark.parametrize("criterion", REG_CRITERIONS)
def test_diabetes_overfit(name, Tree, criterion):
    # check consistency of overfitted trees on the diabetes dataset
    # since the trees will overfit, we expect an MSE of 0
    reg = Tree(criterion=criterion, random_state=0)
    reg.fit(diabetes.data, diabetes.target)
    score = mean_squared_error(diabetes.target, reg.predict(diabetes.data))
    assert score == pytest.approx(0), (
        f"Failed with {name}, criterion = {criterion} and score = {score}"

glemaitre

import pandas as pd
import pytest


def func(expected_columns):

    df = pd.DataFrame({
        "A": [1, 2, 3],
        "B": [1, 2, 3],
        "C": [1, 2, 3]