def check_data(self, data_type='counts', dim='A'):
"""Prints out the highest value count or score for each term.
Parameters
----------
data_type : {'counts', 'score'}
Which data type to use.
dim : {'A', 'B'}, optional
Which set of terms to check.
"""
if data_type not in ['counts', 'score']:
raise ValueError('Data type not understood - can not proceed.')
if data_type == 'score' and self.score.size == 0:
raise ValueError('Score is not computed - can not proceed.')
# Set up which direction to act across
dat = getattr(self, data_type) if dim == 'A' else getattr(
self, data_type).T
alt = 'B' if dim == 'A' and not self.square else 'A'
# Loop through each term, find maximally associated term and print out
for term_ind, term in enumerate(self.terms[dim].labels):
# Find the index of the most common association for current term
assoc_ind = np.argmax(dat[term_ind, :])
print(
"For {:{twd1}} the highest association is {:{twd2}} with {:{nwd}}"
.format(wrap(term),
wrap(self.terms[alt].labels[assoc_ind]),
dat[term_ind, assoc_ind],
twd1=get_max_length(self.terms[dim].labels, 2),
twd2=get_max_length(self.terms[alt].labels, 2),
nwd='>10.0f' if data_type == 'counts' else '06.3f'))
def check_data(self, data_type='counts', dim='A'):
"""Prints out the highest value count or score for each term.
Parameters
----------
data_type : {'counts', 'score'}
Which data type to use.
dim : {'A', 'B'}, optional
Which set of terms to check.
Examples
--------
Print the highest count for each term (assuming `counts` already has data):
>>> counts.check_data() # doctest: +SKIP
Print the highest score value for each term (assuming `counts` already has data):
>>> counts.check_data(data_type='score') # doctest: +SKIP
"""
if not self.has_data:
raise ValueError('No data is available - cannot proceed.')
if data_type not in ['counts', 'score']:
raise ValueError('Data type not understood - can not proceed.')
if data_type == 'score':
if self.score.size == 0:
raise ValueError('Score is not computed - can not proceed.')
if self.score_info['type'] == 'similarity':
raise ValueError(
'Cannot check value counts for similarity score.')
# Set up which direction to act across
data = getattr(self, data_type)
data = data.T if dim == 'B' else data
alt = 'B' if dim == 'A' and not self.square else 'A'
# Calculate widths for printing
twd1 = get_max_length(self.terms[dim].labels, 2)
twd2 = get_max_length(self.terms[alt].labels, 2)
nwd = '>10.0f' if data_type == 'counts' else '06.3f'
# Loop through each term, find maximally associated term and print out
for term_ind, term in enumerate(self.terms[dim].labels):
# Find the index of the most common association for current term
assoc_ind = np.argmax(data[term_ind, :])
print(
"For {:{twd1}} the highest association is {:{twd2}} with {:{nwd}}"
.format(wrap(term),
wrap(self.terms[alt].labels[assoc_ind]),
data[term_ind, assoc_ind],
twd1=twd1,
twd2=twd2,
nwd=nwd))
def check_counts(self, dim='A'):
"""Check how many articles were found for each term.
Parameters
----------
dim : {'A', 'B'}
Which set of terms to check.
Examples
--------
Print the number of articles found for each term (assuming `counts` already has data):
>>> counts.check_counts() # doctest: +SKIP
"""
if not self.has_data:
raise ValueError('No data is available - cannot proceed.')
# Calculate widths for printing
twd = get_max_length(self.terms[dim].labels, 2)
nwd = get_max_length(self.terms[dim].counts)
print("The number of documents found for each search term is:")
for ind, term in enumerate(self.terms[dim].labels):
print(" {:{twd}} - {:{nwd}.0f}".format(
wrap(term), self.terms[dim].counts[ind], twd=twd, nwd=nwd))
def check_top(self, dim='A'):
"""Check the terms with the most articles.
Parameters
----------
dim : {'A', 'B'}, optional
Which set of terms to check.
"""
max_ind = np.argmax(self.terms[dim].counts)
print("The most studied term is {} with {} articles.".format(
wrap(self.terms[dim].labels[max_ind]),
self.terms[dim].counts[max_ind]))
def check_counts(self, dim='A'):
"""Check how many articles were found for each term.
Parameters
----------
dim : {'A', 'B'}, optional
Which set of terms to check.
"""
print("The number of documents found for each search term is:")
for ind, term in enumerate(self.terms[dim].labels):
print(" {:{twd}} - {:{nwd}.0f}".format(
wrap(term),
self.terms[dim].counts[ind],
twd=get_max_length(self.terms[dim].labels, 2),
nwd=get_max_length(self.terms[dim].counts)))
def check_top(self, dim='A'):
"""Check the terms with the most articles.
Parameters
----------
dim : {'A', 'B'}, optional
Which set of terms to check.
Examples
--------
Print which term has the most articles (assuming `counts` already has data):
>>> counts.check_top() # doctest: +SKIP
"""
max_ind = np.argmax(self.terms[dim].counts)
print("The most studied term is {} with {} articles.".format(
wrap(self.terms[dim].labels[max_ind]),
self.terms[dim].counts[max_ind]))
def check_counts(self, dim='A'):
"""Check how many articles were found for each term.
Parameters
----------
dim : {'A', 'B'}, optional
Which set of terms to check.
Examples
--------
Print the number of articles found for each term (assuming `counts` already has data):
>>> counts.check_counts() # doctest: +SKIP
"""
print("The number of documents found for each search term is:")
for ind, term in enumerate(self.terms[dim].labels):
print(" {:{twd}} - {:{nwd}.0f}".format(
wrap(term),
self.terms[dim].counts[ind],
twd=get_max_length(self.terms[dim].labels, 2),
nwd=get_max_length(self.terms[dim].counts)))