Anthony Yoskovich ayoskovich

## top_n.py
df.nlargest(3, 'lat')
df.nsmallest(3, 'lat')

## counts_prop.py
# 'counts' will be the name of the new column
# 'date' will be the index of the dataframe
x = df['date'].value_counts().to_frame('counts')
x['prop'] = x['counts'] / x['counts'].sum()

## format_line.vim
qa0f,100a <Esc>50|dwjq

## jupyter_remove_nums_and_output.py
def scrub_output_pre_save(model, **kwargs):
    """scrub output before saving notebooks"""
    # only run on notebooks
    if model['type'] != 'notebook':
        return
    # only run on nbformat v4
    if model['content']['nbformat'] != 4:
        return

    for cell in model['content']['cells']:

## k_submit.sh
kaggle competitions submit -f <file> -m <message> <competition>

## get_coef.py
pipeline.named_steps['logisticregression'].coef_

## set_reference.py
model = ols("SalePrice ~ C(LandContour, Treatment(reference='Lvl'))", data=df).fit()

## any_greater.py
df[df.apply(lambda x: np.any(x > 100_000), axis=1, raw=True)]

## retina_display.py
%config InlineBackend.figure_format='retina'

## entr_jupyter_notebooks.sh
ls *.ipynb | entr jupyter nbconvert *.ipynb --to python --output-dir=./src
	# 'counts' will be the name of the new column
	# 'date' will be the index of the dataframe
	x = df['date'].value_counts().to_frame('counts')
	x['prop'] = x['counts'] / x['counts'].sum()
	def scrub_output_pre_save(model, **kwargs):
	"""scrub output before saving notebooks"""
	# only run on notebooks
	if model['type'] != 'notebook':
	return
	# only run on nbformat v4
	if model['content']['nbformat'] != 4:
	return

	for cell in model['content']['cells']: