lewtun

## datasets-wikiann.ipynb

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                lewtun
                / datasets-wikiann.ipynb
            
            
              Last active
              December 5, 2020 19:02
            
              
                Snippets to produce dummy data for WikiANN in HF datasets
              
          
      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## Makefile
.PHONY: install

#################################################################################
# GLOBALS                                                                       #
#################################################################################
SHELL=/bin/bash
CONDA_ACTIVATE=source $$(conda info --base)/etc/profile.d/conda.sh ; conda activate ; conda activate

#################################################################################
# COMMANDS                                                                      #

## Makefile
# Copyight 2016 drivendata
# Copyright 2019 fast.ai
# Copyright 2020 Lewis Tunstall

# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at

#    http://www.apache.org/licenses/LICENSE-2.0

## mnist-sample-7
sample

## mnist-sample-3
sample

## template_transformer.py
class TemplateTransformer(BaseEstimator, TransformerMixin):
    """ An example transformer that returns the element-wise square root."""
    def __init__(self, demo_param='demo'):
        self.demo_param = demo_param

    def fit(self, X, y=None):
        """A reference implementation of a fitting function for a transformer."""
        X = check_array(X, accept_sparse=True)

        self.n_features_ = X.shape[1]

## cv_model.py
def cv_model(X, y, features, n_fold=5, random_state=45245, params=None):
    """Evaluate a score by cross validation.

    Parameters
    ----------

    X : pandas.DataFrame
        The data to fit.

    y : pandas.DataFrame or pandas.Series

## average_lifetime.py
import pandas as pd

# define topological features to track
homology_dimensions = [0, 1, 2]

# calculate persistence diagram
persistence_diagram = ...

# convert NumPy array of triples to DataFrame
persistence_table = pd.DataFrame(

## persistence_amplitude.py
import gtda.diagrams as diagrams

# calculate persistence diagram
persistence_diagram = ...

# define type of amplitude to calculate
amplitude = diagrams.Amplitude(metric="wasserstein")

# calculate amplitude of diagram
persistence_diagram_amplitude = amplitude.fit_transform(persistence_diagram)

## persistence_distance_matrix.py
import gtda.homology as hl

# represent data as a matrix of pairwise distances
distance_matrix = ...

# define topological features to track
homology_dimensions = [0, 1, 2]

# define simplicial complex to construct
persistence = hl.VietorisRipsPersistence(
	.PHONY: install

	#################################################################################
	# GLOBALS #
	#################################################################################
	SHELL=/bin/bash
	CONDA_ACTIVATE=source $$(conda info --base)/etc/profile.d/conda.sh ; conda activate ; conda activate

	#################################################################################
	# COMMANDS #
	# Copyight 2016 drivendata
	# Copyright 2019 fast.ai
	# Copyright 2020 Lewis Tunstall

	# Licensed under the Apache License, Version 2.0 (the "License");
	# you may not use this file except in compliance with the License.
	# You may obtain a copy of the License at

	# http://www.apache.org/licenses/LICENSE-2.0
	class TemplateTransformer(BaseEstimator, TransformerMixin):
	""" An example transformer that returns the element-wise square root."""
	def __init__(self, demo_param='demo'):
	self.demo_param = demo_param

	def fit(self, X, y=None):
	"""A reference implementation of a fitting function for a transformer."""
	X = check_array(X, accept_sparse=True)

	self.n_features_ = X.shape[1]
	def cv_model(X, y, features, n_fold=5, random_state=45245, params=None):
	"""Evaluate a score by cross validation.

	Parameters
	----------

	X : pandas.DataFrame
	The data to fit.

	y : pandas.DataFrame or pandas.Series
	import pandas as pd

	# define topological features to track
	homology_dimensions = [0, 1, 2]

	# calculate persistence diagram
	persistence_diagram = ...

	# convert NumPy array of triples to DataFrame
	persistence_table = pd.DataFrame(
	import gtda.diagrams as diagrams

	# calculate persistence diagram
	persistence_diagram = ...

	# define type of amplitude to calculate
	amplitude = diagrams.Amplitude(metric="wasserstein")

	# calculate amplitude of diagram
	persistence_diagram_amplitude = amplitude.fit_transform(persistence_diagram)
	import gtda.homology as hl

	# represent data as a matrix of pairwise distances
	distance_matrix = ...

	# define topological features to track
	homology_dimensions = [0, 1, 2]

	# define simplicial complex to construct
	persistence = hl.VietorisRipsPersistence(