scipy-yli/yli/utils.py

#   scipy-yli: Helpful SciPy utilities and recipes
#   Copyright © 2022  Lee Yingtong Li (RunasSudo)
#
#   This program is free software: you can redistribute it and/or modify
#   it under the terms of the GNU Affero General Public License as published by
#   the Free Software Foundation, either version 3 of the License, or
#   (at your option) any later version.
#
#   This program is distributed in the hope that it will be useful,
#   but WITHOUT ANY WARRANTY; without even the implied warranty of
#   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
#   GNU Affero General Public License for more details.
#
#   You should have received a copy of the GNU Affero General Public License
#   along with this program.  If not, see <https://www.gnu.org/licenses/>.

import numpy as np
import pandas as pd
import patsy

import warnings

from .config import config

# ----------------------------
# Data cleaning and validation

def check_nan(df, nan_policy):
	"""Check df against nan_policy and return cleaned input"""
	
	if nan_policy == 'raise':
		if pd.isna(df).any(axis=None):
			raise ValueError('NaN in input, pass nan_policy="warn" or "omit" to ignore')
		return df
	elif nan_policy == 'warn':
		df_cleaned = df.dropna()
		if len(df_cleaned) < len(df):
			warnings.warn('Omitting {} rows with NaN'.format(len(df) - len(df_cleaned)))
		return df_cleaned
	elif nan_policy == 'omit':
		return df.dropna()
	else:
		raise Exception('Invalid nan_policy, expected "raise", "warn" or "omit"')

def convert_pandas_nullable(df):
	"""Convert pandas nullable dtypes (e.g. Int64) to non-nullable numpy dtypes"""
	
	# TODO: Can we avoid this copy?
	df = df.copy()
	
	for col in df.columns:
		if df[col].dtype == 'Int64':
			df[col] = df[col].astype('int')
	
	return df

def as_2groups(df, data, group):
	"""Group the data by the given variable, ensuring only 2 groups"""
	
	# Get groupings
	groups = list(df.groupby(group).groups.items())
	
	# Ensure only 2 groups to compare
	if len(groups) != 2:
		raise Exception('Got {} values for {}, expected 2'.format(len(groups), group))
	
	# Get 2 groups
	group1 = groups[0][0]
	data1 = df.loc[groups[0][1], data]
	group2 = groups[1][0]
	data2 = df.loc[groups[1][1], data]
	
	return group1, data1, group2, data2

# ----------
# Formatting

def do_fmt_p(p):
	"""Return sign and formatted p value"""
	
	if p < 10**-config.pvalue_max_dps:
		# Smaller than min value
		return '<', '{:.1g}'.format(10**-config.pvalue_max_dps)
	
	if p > 1 - 10**-config.pvalue_min_dps:
		# Larger than max value
		return '>', '{0:.{dps}f}'.format(1 - 10**-config.pvalue_min_dps, dps=config.pvalue_min_dps)
	
	if round(p, config.pvalue_min_dps) == config.alpha:
		# Rounding to pvalue_min_dps makes significance ambiguous
		
		if round(p, config.pvalue_max_dps) == config.alpha:
			# Still ambiguous to pvalue_max_dps
			
			if p < config.alpha:
				# Significant: round down
				p = config.alpha - 10**-config.pvalue_max_dps
			else:
				# Nonsignificant: round up
				p = config.alpha + 10**-config.pvalue_max_dps
		
		return '', '{0:.{dps}f}'.format(p, dps=config.pvalue_max_dps)
	
	if p < 10**-config.pvalue_min_dps:
		# Insufficient resolution at pvalue_min_dps
		# We know from earlier comparison that 1 s.f. fits within pvalue_max_dps
		return '', '{:.1g}'.format(p)
	
	# OK to round to pvalue_min_dps
	return '', '{0:.{dps}f}'.format(p, dps=config.pvalue_min_dps)

def fmt_p(p, *, html, only_value=False, tabular=False):
	"""
	Format p value
	
	tabular: If true, output in ‘tabular’ format of p values where decimal points align
	"""
	
	# FIXME: Make only_value and tabular enums
	
	sign, fmt = do_fmt_p(p)
	
	# Strip leading zero if required
	if not config.pvalue_leading_zero:
		fmt = fmt.lstrip('0')
	
	# Check if significant
	if p < config.alpha:
		asterisk = '*'
	else:
		asterisk = ''
	
	if html:
		# Escape angle quotes
		sign = sign.replace('<', '&lt;')
		sign = sign.replace('>', '&gt;')
		
		if only_value:
			return '{}{}{}'.format(sign, fmt, asterisk)
		elif tabular:
			# Always left-aligned, so reserve space for sign if required to align decimal points
			if not sign:
				sign = '<span style="visibility:hidden">=</span>'
			
			return '{}{}{}'.format(sign, fmt, asterisk)
		else:
			# Non-tabular so force a sign
			if not sign:
				sign = '='
			return '{} {}{}'.format(sign, fmt, asterisk)
	else:
		if only_value:
			return '{}{}{}'.format(sign, fmt, asterisk)
		elif tabular:
			# Right-aligned, so add spaces to simulate left alignment
			if not sign:
				sign = ' '
			
			# +1 for decimal point
			# +1 for sign
			# +1 for asterisk
			pvalue_max_len = config.pvalue_max_dps + 3
			if config.pvalue_leading_zero:
				pvalue_max_len += 1
			
			# Now add spaces
			rpadding = ' ' * (pvalue_max_len - len(sign + fmt + asterisk))
			
			return '{}{}{}{}'.format(sign, fmt, asterisk, rpadding)
		else:
			# Non-tabular so force a sign
			if not sign:
				sign = '='
			return '{} {}{}'.format(sign, fmt, asterisk)

# ------------------------------
# General result-related classes

class ConfidenceInterval:
	"""A confidence interval"""
	
	def __init__(self, lower, upper):
		#: Lower confidence limit (*float*)
		self.lower = lower
		#: Upper confidence limit (*float*)
		self.upper = upper
	
	def __repr__(self):
		if config.repr_is_summary:
			return self.summary()
		return super().__repr__()
	
	def _repr_html_(self):
		return self.summary()
	
	def summary(self):
		"""
		Return a stringified summary of the confidence interval
		
		:rtype: str
		"""
		
		return '{:.2f}–{:.2f}'.format(self.lower, self.upper)

class Estimate:
	"""A point estimate and surrounding confidence interval"""
	
	def __init__(self, point, ci_lower, ci_upper):
		#: Point estimate (*float*)
		self.point = point
		#: Lower confidence limit (*float*)
		self.ci_lower = ci_lower
		#: Upper confidence limit (*float*)
		self.ci_upper = ci_upper
	
	def __repr__(self):
		if config.repr_is_summary:
			return self.summary()
		return super().__repr__()
	
	def _repr_html_(self):
		return self.summary()
	
	def summary(self):
		"""
		Return a stringified summary of the estimate and confidence interval
		
		:rtype: str
		"""
		
		return '{:.2f} ({:.2f}–{:.2f})'.format(self.point, self.ci_lower, self.ci_upper)
	
	def __neg__(self):
		return Estimate(-self.point, -self.ci_upper, -self.ci_lower)
	
	def __abs__(self):
		if self.point < 0:
			return -self
		else:
			return self
	
	def exp(self):
		return Estimate(np.exp(self.point), np.exp(self.ci_lower), np.exp(self.ci_upper))

# --------------------------
# Patsy formula manipulation

def cols_for_formula(formula, df):
	"""Return the columns corresponding to the Patsy formula"""
	
	# Parse the formula
	model_desc = patsy.ModelDesc.from_formula(formula)
	
	# Get the columns
	cols = set()
	for term in model_desc.rhs_termlist:
		for factor in term.factors:
			name = factor.name()
			if name.startswith('C('):
				# Contrasts expression
				# Get the corresponding factor_info
				factor_info = formula_get_factor_info(formula, df, name)
				
				# Evaluate the factor
				categorical_box = factor_info.factor.eval(factor_info.state, df)
				
				# Get the column name
				name = categorical_box.data.name
			
			cols.add(name)
	
	return list(cols)

def formula_get_factor_info(formula, df, factor):
	"""Get the FactorInfo for a factor in a Patsy formula"""
	
	# Parse the formula
	design_info = patsy.dmatrix(formula, df).design_info
	
	# Get the corresponding factor_info
	factor_info = next(v for k, v in design_info.factor_infos.items() if k.name() == factor)
	return factor_info

def formula_factor_ref_category(formula, df, factor):
	"""Get the reference category for a term in a Patsy formula referring to a categorical factor"""
	
	if '(' in factor and not factor.startswith('C('):
		raise Exception('Attempted to get reference category for unknown expression type "{}"'.format(factor))
	
	# Get the factor_info
	factor_info = formula_get_factor_info(formula, df, factor)
	
	if '(' not in factor:
		# C(...) is not specified, so must be default
		return factor_info.categories[0]
	
	# Evaluate the factor
	categorical_box = factor_info.factor.eval(factor_info.state, df)
	
	if categorical_box.contrast is None or categorical_box.contrast is patsy.Treatment:
		# Default Treatment contrast with default reference group: first category
		return factor_info.categories[0]
	
	if isinstance(categorical_box.contrast, patsy.Treatment):
		if categorical_box.contrast.reference is None:
			# Default reference group: first category
			return factor_info.categories[0]
		
		# Specified reference group
		return categorical_box.contrast.reference
	
	raise Exception('Attempted to get reference category for unknown contrast type {}'.format(categorical_box.contrast.__class__.__name__))

def parse_patsy_term(formula, df, term):
	"""
	Parse a Patsy term into its component parts
	
	Returns: factor, column, contrast
	e.g. "C(x, Treatment(y))[T.z]" -> "C(x, Treatment(y))", "x", "z"
	"""
	
	if '(' not in term:
		if '[' in term:
			if '[T.' not in term:
				raise Exception('Attempted to parse term for unknown contrast type "{}"'.format(term))
			
			# Treatment contrast term
			factor = term[:term.index('[T.')]
			contrast = term[term.index('[T.')+3:term.index(']')]
			
			return factor, factor, contrast
		else:
			# Nothing special
			return term, term, None
	
	# Term contains '('
	
	if not term.startswith('C('):
		raise Exception('Attempted to parse term for unknown expression type "{}"'.format(term))
	
	if '[' in term:
		if '[T.' not in term:
			raise Exception('Attempted to parse term for unknown contrast type "{}"'.format(term))
		
		# Treatment contrast term
		factor = term[:term.index('[T.')]
		contrast = term[term.index('[T.')+3:term.index(']')]
	else:
		# Not a treatment contrast (I think this is impossible?)
		raise Exception('Attempted to parse unsupported contrast-like term with no contrasts')
	
	factor_inner = factor[factor.index('(')+1:factor.rindex(')')]
	if ',' in factor_inner:
		column = factor_inner[:factor_inner.index(',')]
	else:
		column = factor_inner
	
	return factor, column, contrast