def test_eval_matches_valid_2(self):
A = read_csv_metadata(path_a)
B = read_csv_metadata(path_b, key='ID')
C = read_csv_metadata(path_c, ltable=A, rtable=B)
C1 = C[['_id', 'ltable_ID', 'rtable_ID']]
num_ones = 1
num_zeros = len(C1) - num_ones
gold = [0] * num_ones
gold.extend([1] * num_zeros)
predicted = [1] * (num_zeros + num_ones)
ln = len(C1.columns)
C1.insert(ln, 'gold', gold)
C1.insert(ln + 1, 'predicted', predicted)
cm.copy_properties(C, C1)
result = eval_matches(C1, 'predicted', 'gold')
self.assertEqual(isinstance(result, dict), True)
self.assertEqual(result['prec_numerator'], 14)
self.assertEqual(result['prec_denominator'], 14)
self.assertAlmostEqual(result['precision'], 1)
self.assertEqual(result['recall_numerator'], 14)
self.assertEqual(result['recall_denominator'], 15)
self.assertEqual(result['recall'], 0.9333333333333333)
self.assertEqual(result['f1'], 0.9655172413793104)
self.assertEqual(result['pred_pos_num'], 14)
self.assertEqual(result['false_pos_num'], 0.0)
self.assertEqual(len(result['false_pos_ls']), 0)
self.assertEqual(result['pred_neg_num'], 1)
self.assertEqual(result['false_neg_num'], 1.0)
self.assertEqual(len(result['false_neg_ls']), 1)
t = result['false_neg_ls'][0]
self.assertEqual(t[0], 'a1')
self.assertEqual(t[1], 'b1')
def _post_process_labelled_table(input_table, labeled_table, col_name):
"""
This function post processes the labeled table and updates the catalog.
Specifically, this function validates that the label column contain only
0 and 1's, and finally copies the properties from the input table to the
output table.
"""
# Cast the label values to int as initially they will be strings when it
# comes from the GUI
labeled_table[col_name] = labeled_table[col_name].astype(int)
# Check if the table contains only 0s and 1s
label_value_with_1 = labeled_table[col_name] == 1
label_value_with_0 = labeled_table[col_name] == 0
sum_of_labels = sum(label_value_with_1 | label_value_with_0)
# If they contain column values other than 0 and 1, raise an error
if not sum_of_labels == len(labeled_table):
logger.error('The label column contains values other than 0 and 1')
raise AssertionError(
'The label column contains values other than 0 and 1')
# Copy the properties from the input table to label table.
# Note: Here we dont have to check for the integrity of 'key' because the
# key column is not tampered from the input table.
cm.init_properties(labeled_table)
cm.copy_properties(input_table, labeled_table)
# Return the label table
return labeled_table
def test_eval_matches_valid_3(self):
A = read_csv_metadata(path_a)
B = read_csv_metadata(path_b, key='ID')
C = read_csv_metadata(path_c, ltable=A, rtable=B)
C1 = C[['_id', 'ltable_ID', 'rtable_ID']]
num_ones = len(C1)
num_zeros = len(C1) - num_ones
gold = [0]*num_ones
# gold.extend([1]*num_zeros)
predicted = [1]* (num_zeros + num_ones)
ln = len(C1.columns)
C1.insert(ln, 'gold', gold)
C1.insert(ln+1, 'predicted', predicted)
D = pd.DataFrame(columns=C1.columns)
cm.copy_properties(C, D)
result = eval_matches(D, 'gold', 'predicted')
self.assertEqual(isinstance(result, dict), True)
self.assertEqual(result['prec_numerator'], 0)
self.assertEqual(result['prec_denominator'], 0)
self.assertAlmostEqual(result['precision'], 0)
self.assertEqual(result['recall_numerator'], 0)
self.assertEqual(result['recall_denominator'], 0)
self.assertEqual(result['recall'], 0)
self.assertEqual(result['f1'], 0)
self.assertEqual(result['pred_pos_num'], 0)
self.assertEqual(result['false_pos_num'], 0.0)
self.assertEqual(len(result['false_pos_ls']), 0)
self.assertEqual(result['pred_neg_num'], 0)
self.assertEqual(result['false_neg_num'], 0.0)
self.assertEqual(len(result['false_neg_ls']), 0)
def predict(self, x=None, table=None, exclude_attrs=None, target_attr=None, append=False, inplace=True):
if x is not None:
y = self.predict_sklearn(x)
# if table is not None and target_attr is not None and append is True:
# if inplace == True:
# table[target_attr] = y
# return table
# else:
# tbl = table.copy()
# tbl[target_attr] = y
# return tbl
elif table is not None and exclude_attrs is not None:
y = self.predict_ex_attrs(table, exclude_attrs)
if target_attr is not None and append is True:
if inplace == True:
table[target_attr] = y
return table
else:
tbl = table.copy()
tbl[target_attr] = y
cm.copy_properties(table, tbl)
return tbl
else:
raise SyntaxError('The arguments supplied does not match the signatures supported !!!')
return y
def test_eval_matches_valid_3(self):
A = read_csv_metadata(path_a)
B = read_csv_metadata(path_b, key='ID')
C = read_csv_metadata(path_c, ltable=A, rtable=B)
C1 = C[['_id', 'ltable_ID', 'rtable_ID']]
num_ones = len(C1)
num_zeros = len(C1) - num_ones
gold = [0] * num_ones
# gold.extend([1]*num_zeros)
predicted = [1] * (num_zeros + num_ones)
ln = len(C1.columns)
C1.insert(ln, 'gold', gold)
C1.insert(ln + 1, 'predicted', predicted)
D = pd.DataFrame(columns=C1.columns)
cm.copy_properties(C, D)
result = eval_matches(D, 'gold', 'predicted')
self.assertEqual(isinstance(result, dict), True)
self.assertEqual(result['prec_numerator'], 0)
self.assertEqual(result['prec_denominator'], 0)
self.assertAlmostEqual(result['precision'], 0)
self.assertEqual(result['recall_numerator'], 0)
self.assertEqual(result['recall_denominator'], 0)
self.assertEqual(result['recall'], 0)
self.assertEqual(result['f1'], 0)
self.assertEqual(result['pred_pos_num'], 0)
self.assertEqual(result['false_pos_num'], 0.0)
self.assertEqual(len(result['false_pos_ls']), 0)
self.assertEqual(result['pred_neg_num'], 0)
self.assertEqual(result['false_neg_num'], 0.0)
self.assertEqual(len(result['false_neg_ls']), 0)
def predict(self,
x=None,
table=None,
exclude_attrs=None,
target_attr=None,
append=False,
inplace=True):
if x is not None:
y = self.predict_sklearn(x)
# if table is not None and target_attr is not None and append is True:
# if inplace == True:
# table[target_attr] = y
# return table
# else:
# tbl = table.copy()
# tbl[target_attr] = y
# return tbl
elif table is not None and exclude_attrs is not None:
y = self.predict_ex_attrs(table, exclude_attrs)
if target_attr is not None and append is True:
if inplace == True:
table[target_attr] = y
return table
else:
tbl = table.copy()
tbl[target_attr] = y
cm.copy_properties(table, tbl)
return tbl
else:
raise SyntaxError(
'The arguments supplied does not match the signatures supported !!!'
)
return y
def _post_process_labelled_table(input_table, labeled_table, col_name):
"""
This function post processes the labeled table and updates the catalog.
Specifically, this function validates that the label column contain only
0 and 1's, and finally copies the properties from the input table to the
output table.
"""
# Cast the label values to int as initially they will be strings when it
# comes from the GUI
labeled_table[col_name] = labeled_table[col_name].astype(int)
# Check if the table contains only 0s and 1s
label_value_with_1 = labeled_table[col_name] == 1
label_value_with_0 = labeled_table[col_name] == 0
sum_of_labels = sum(label_value_with_1 | label_value_with_0)
# If they contain column values other than 0 and 1, raise an error
if not sum_of_labels == len(labeled_table):
logger.error('The label column contains values other than 0 and 1')
raise AssertionError(
'The label column contains values other than 0 and 1')
# Copy the properties from the input table to label table.
# Note: Here we dont have to check for the integrity of 'key' because the
# key column is not tampered from the input table.
cm.init_properties(labeled_table)
cm.copy_properties(input_table, labeled_table)
# Return the label table
return labeled_table
def add_output_attributes(candset, l_output_attrs=None, r_output_attrs=None, l_output_prefix='ltable_',
r_output_prefix='rtable_', validate=True, copy_props=True,
delete_from_catalog=True, verbose=False):
if not isinstance(candset, pd.DataFrame):
logger.error('Input object is not of type pandas data frame')
raise AssertionError('Input object is not of type pandas data frame')
# # get metadata
key, fk_ltable, fk_rtable, ltable, rtable, l_key, r_key = cm.get_metadata_for_candset(candset, logger, verbose)
if validate:
cm.validate_metadata_for_candset(candset, key, fk_ltable, fk_rtable, ltable, rtable, l_key, r_key,
logger, verbose)
index_values = candset.index
df = _add_output_attributes(candset, fk_ltable, fk_rtable, ltable, rtable, l_key, r_key,
l_output_attrs, r_output_attrs, l_output_prefix, r_output_prefix,
validate=False)
df.set_index(index_values, inplace=True)
if copy_props:
cm.init_properties(df)
cm.copy_properties(candset, df)
if delete_from_catalog:
cm.del_all_properties(candset)
return df
def test_eval_matches_valid_2(self):
A = read_csv_metadata(path_a)
B = read_csv_metadata(path_b, key='ID')
C = read_csv_metadata(path_c, ltable=A, rtable=B)
C1 = C[['_id', 'ltable_ID', 'rtable_ID']]
num_ones = 1
num_zeros = len(C1) - num_ones
gold = [0] * num_ones
gold.extend([1] * num_zeros)
predicted = [1] * (num_zeros + num_ones)
ln = len(C1.columns)
C1.insert(ln, 'gold', gold)
C1.insert(ln + 1, 'predicted', predicted)
cm.copy_properties(C, C1)
result = eval_matches(C1, 'predicted', 'gold')
self.assertEqual(isinstance(result, dict), True)
self.assertEqual(result['prec_numerator'], 14)
self.assertEqual(result['prec_denominator'], 14)
self.assertAlmostEqual(result['precision'], 1)
self.assertEqual(result['recall_numerator'], 14)
self.assertEqual(result['recall_denominator'], 15)
self.assertEqual(result['recall'], 0.9333333333333333)
self.assertEqual(result['f1'], 0.9655172413793104)
self.assertEqual(result['pred_pos_num'], 14)
self.assertEqual(result['false_pos_num'], 0.0)
self.assertEqual(len(result['false_pos_ls']), 0)
self.assertEqual(result['pred_neg_num'], 1)
self.assertEqual(result['false_neg_num'], 1.0)
self.assertEqual(len(result['false_neg_ls']), 1)
t = result['false_neg_ls'][0]
self.assertEqual(t[0], 'a1')
self.assertEqual(t[1], 'b1')
def test_copy_properties_update_false_2(self):
A = read_csv_metadata(path_a)
A1 = pd.read_csv(path_a)
cm.copy_properties(A, A1, update=False)
p = cm.get_all_properties(A)
p1 = cm.get_all_properties(A1)
self.assertEqual(p, p1)
self.assertEqual(cm.get_key(A1), cm.get_key(A))
def test_copy_properties_valid_1(self):
A = read_csv_metadata(path_a)
A1 = pd.read_csv(path_a)
cm.copy_properties(A, A1)
self.assertEqual(cm.is_dfinfo_present(A1), True)
p = cm.get_all_properties(A)
p1 = cm.get_all_properties(A1)
self.assertEqual(p, p1)
self.assertEqual(cm.get_key(A1), cm.get_key(A))
def train_test_split(labeled_data,
train_proportion=0.5,
random_state=None,
verbose=True):
if not isinstance(labeled_data, pd.DataFrame):
logger.error('Input table is not of type dataframe')
raise AssertionError('Input table is not of type dataframe')
log_info(
logger, 'Required metadata: cand.set key, fk ltable, fk rtable, '
'ltable, rtable, ltable key, rtable key', verbose)
# # get metadata
key, fk_ltable, fk_rtable, ltable, rtable, l_key, r_key = cm.get_metadata_for_candset(
labeled_data, logger, verbose)
# # validate metadata
cm.validate_metadata_for_candset(labeled_data, key, fk_ltable, fk_rtable,
ltable, rtable, l_key, r_key, logger,
verbose)
num_rows = len(labeled_data)
assert train_proportion >= 0 and train_proportion <= 1, " Train proportion is expected to be between 0 and 1"
assert num_rows > 0, 'The input table is empty'
train_size = int(math.floor(num_rows * train_proportion))
test_size = int(num_rows - train_size)
# use sk learn to split the data
idx_values = pd.np.array(labeled_data.index.values)
idx_train, idx_test = cv.train_test_split(idx_values,
test_size=test_size,
train_size=train_size,
random_state=random_state)
# construct output tables.
lbl_train = labeled_data.ix[idx_train]
lbl_test = labeled_data.ix[idx_test]
# update catalog
cm.init_properties(lbl_train)
cm.copy_properties(labeled_data, lbl_train)
cm.init_properties(lbl_test)
cm.copy_properties(labeled_data, lbl_test)
# return output tables
result = OrderedDict()
result['train'] = lbl_train
result['test'] = lbl_test
return result
def _test_label_table(self, table, col_name, label_values):
_validate_inputs(table, col_name, verbose=False)
lbl_table = _init_label_table(table, col_name)
from magellan.gui.table_gui import edit_table
edit_table(lbl_table, show_flag=False)
new_table = lbl_table.copy()
cm.copy_properties(table, new_table)
lbl_table = new_table
lbl_table[col_name] = label_values
lbl_table = _post_process_labelled_table(table, lbl_table, col_name)
return lbl_table
def _test_label_table(self, table, col_name, label_values):
_validate_inputs(table, col_name, verbose=False)
lbl_table = _init_label_table(table, col_name)
from magellan.gui.table_gui import edit_table
edit_table(lbl_table, show_flag=False)
new_table = lbl_table.copy()
cm.copy_properties(table, new_table)
lbl_table = new_table
lbl_table[col_name] = label_values
lbl_table = _post_process_labelled_table(table, lbl_table, col_name)
return lbl_table
def test_copy_properties_valid_2(self):
A = read_csv_metadata(path_a)
B = read_csv_metadata(path_b)
C = read_csv_metadata(path_c, ltable=A, rtable=B)
C1 = pd.read_csv(path_c)
cm.copy_properties(C, C1)
self.assertEqual(cm.is_dfinfo_present(C1), True)
p = cm.get_all_properties(C1)
p1 = cm.get_all_properties(C1)
self.assertEqual(p, p1)
self.assertEqual(cm.get_key(C1), cm.get_key(C))
self.assertEqual(cm.get_ltable(C1).equals(A), True)
self.assertEqual(cm.get_rtable(C1).equals(B), True)
self.assertEqual(cm.get_fk_ltable(C1), cm.get_fk_ltable(C))
self.assertEqual(cm.get_fk_rtable(C1), cm.get_fk_rtable(C))
def test_eval_matches_predicted_attr_not_in_df(self):
A = read_csv_metadata(path_a)
B = read_csv_metadata(path_b, key='ID')
C = read_csv_metadata(path_c, ltable=A, rtable=B)
C1 = C[['_id', 'ltable_ID', 'rtable_ID']]
num_ones = 1
num_zeros = len(C1) - num_ones
gold = [0] * num_ones
gold.extend([1] * num_zeros)
predicted = [1] * (num_zeros + num_ones)
ln = len(C1.columns)
C1.insert(ln, 'gold', gold)
C1.insert(ln + 1, 'predicted', predicted)
cm.copy_properties(C, C1)
result = eval_matches(C1, 'gold', 'predicted1')
def test_eval_matches_predicted_attr_not_in_df(self):
A = read_csv_metadata(path_a)
B = read_csv_metadata(path_b, key='ID')
C = read_csv_metadata(path_c, ltable=A, rtable=B)
C1 = C[['_id', 'ltable_ID', 'rtable_ID']]
num_ones = 1
num_zeros = len(C1) - num_ones
gold = [0] * num_ones
gold.extend([1] * num_zeros)
predicted = [1] * (num_zeros + num_ones)
ln = len(C1.columns)
C1.insert(ln, 'gold', gold)
C1.insert(ln + 1, 'predicted', predicted)
cm.copy_properties(C, C1)
result = eval_matches(C1, 'gold', 'predicted1')
def add_output_attributes(candset,
l_output_attrs=None,
r_output_attrs=None,
l_output_prefix='ltable_',
r_output_prefix='rtable_',
validate=True,
copy_props=True,
delete_from_catalog=True,
verbose=False):
if not isinstance(candset, pd.DataFrame):
logger.error('Input object is not of type pandas data frame')
raise AssertionError('Input object is not of type pandas data frame')
# # get metadata
key, fk_ltable, fk_rtable, ltable, rtable, l_key, r_key = cm.get_metadata_for_candset(
candset, logger, verbose)
if validate:
cm.validate_metadata_for_candset(candset, key, fk_ltable, fk_rtable,
ltable, rtable, l_key, r_key, logger,
verbose)
index_values = candset.index
df = _add_output_attributes(candset,
fk_ltable,
fk_rtable,
ltable,
rtable,
l_key,
r_key,
l_output_attrs,
r_output_attrs,
l_output_prefix,
r_output_prefix,
validate=False)
df.set_index(index_values, inplace=True)
if copy_props:
cm.init_properties(df)
cm.copy_properties(candset, df)
if delete_from_catalog:
cm.del_all_properties(candset)
return df
def extract_feature_vecs(candset, attrs_before=None, feature_table=None, attrs_after=None, verbose=True):
if not isinstance(candset, pd.DataFrame):
logger.error('Input cand.set is not of type dataframe')
raise AssertionError('Input cand.set is not of type dataframe')
# validate input parameters
if attrs_before != None:
if not check_attrs_present(candset, attrs_before):
logger.error('The attributes mentioned in attrs_before is not present ' \
'in the input table')
raise AssertionError('The attributes mentioned in attrs_before is not present ' \
'in the input table')
if attrs_after != None:
if not check_attrs_present(candset, attrs_after):
logger.error('The attributes mentioned in attrs_after is not present ' \
'in the input table')
raise AssertionError('The attributes mentioned in attrs_after is not present ' \
'in the input table')
if feature_table is None:
logger.error('Feature table cannot be null')
raise AssertionError('The feature table cannot be null')
log_info(logger, 'Required metadata: cand.set key, fk ltable, fk rtable, '
'ltable, rtable, ltable key, rtable key', verbose)
# # get metadata
key, fk_ltable, fk_rtable, ltable, rtable, l_key, r_key = cm.get_metadata_for_candset(candset, logger, verbose)
# # validate metadata
cm.validate_metadata_for_candset(candset, key, fk_ltable, fk_rtable, ltable, rtable, l_key, r_key,
logger, verbose)
# extract features
id_list = [(r[fk_ltable], r[fk_rtable]) for i, r in candset.iterrows()]
# # set index for convenience
l_df = ltable.set_index(l_key, drop=False)
r_df = rtable.set_index(r_key, drop=False)
# # apply feature functions
feat_vals = [apply_feat_fns(l_df.ix[x[0]], r_df.ix[x[1]], feature_table) for x in id_list]
# construct output table
table = pd.DataFrame(feat_vals)
# # rearrange the feature names in the given order
feat_names = list(feature_table['feature_name'])
table = table[feat_names]
# # insert attrs_before
if attrs_before:
if not isinstance(attrs_before, list):
attrs_before = [attrs_before]
attrs_before = list_diff(attrs_before, [key, fk_ltable, fk_rtable])
attrs_before.reverse()
for a in attrs_before:
table.insert(0, a, candset[a])
# # insert keys
table.insert(0, fk_rtable, candset[fk_rtable])
table.insert(0, fk_ltable, candset[fk_ltable])
table.insert(0, key, candset[key])
# # insert attrs after
if attrs_after:
if not isinstance(attrs_after, list):
attrs_after = [attrs_after]
attrs_after = list_diff(attrs_after, [key, fk_ltable, fk_rtable])
attrs_after.reverse()
col_pos = len(table.columns)
for a in attrs_after:
table.insert(col_pos, a, candset[a])
col_pos += 1
# reset the index
table.reset_index(inplace=True, drop=True)
# # update the catalog
cm.init_properties(table)
cm.copy_properties(candset, table)
return table
import magellan as mg
import pandas as pd
import magellan.catalog.catalog_manager as cm
A = mg.load_dataset('table_A')
B = pd.read_csv('../magellan/datasets/B.csv')
cm.init_properties(B)
cm.copy_properties(A, B)
print 'hi'
def extract_feature_vecs(candset,
attrs_before=None,
feature_table=None,
attrs_after=None,
verbose=True):
if not isinstance(candset, pd.DataFrame):
logger.error('Input cand.set is not of type dataframe')
raise AssertionError('Input cand.set is not of type dataframe')
# validate input parameters
if attrs_before != None:
if not check_attrs_present(candset, attrs_before):
logger.error('The attributes mentioned in attrs_before is not present ' \
'in the input table')
raise AssertionError('The attributes mentioned in attrs_before is not present ' \
'in the input table')
if attrs_after != None:
if not check_attrs_present(candset, attrs_after):
logger.error('The attributes mentioned in attrs_after is not present ' \
'in the input table')
raise AssertionError('The attributes mentioned in attrs_after is not present ' \
'in the input table')
if feature_table is None:
logger.error('Feature table cannot be null')
raise AssertionError('The feature table cannot be null')
log_info(
logger, 'Required metadata: cand.set key, fk ltable, fk rtable, '
'ltable, rtable, ltable key, rtable key', verbose)
# # get metadata
key, fk_ltable, fk_rtable, ltable, rtable, l_key, r_key = cm.get_metadata_for_candset(
candset, logger, verbose)
# # validate metadata
cm.validate_metadata_for_candset(candset, key, fk_ltable, fk_rtable,
ltable, rtable, l_key, r_key, logger,
verbose)
# extract features
id_list = [(r[fk_ltable], r[fk_rtable]) for i, r in candset.iterrows()]
# # set index for convenience
l_df = ltable.set_index(l_key, drop=False)
r_df = rtable.set_index(r_key, drop=False)
# # apply feature functions
feat_vals = [
apply_feat_fns(l_df.ix[x[0]], r_df.ix[x[1]], feature_table)
for x in id_list
]
# construct output table
table = pd.DataFrame(feat_vals)
# # rearrange the feature names in the given order
feat_names = list(feature_table['feature_name'])
table = table[feat_names]
# # insert attrs_before
if attrs_before:
if not isinstance(attrs_before, list):
attrs_before = [attrs_before]
attrs_before = list_diff(attrs_before, [key, fk_ltable, fk_rtable])
attrs_before.reverse()
for a in attrs_before:
table.insert(0, a, candset[a])
# # insert keys
table.insert(0, fk_rtable, candset[fk_rtable])
table.insert(0, fk_ltable, candset[fk_ltable])
table.insert(0, key, candset[key])
# # insert attrs after
if attrs_after:
if not isinstance(attrs_after, list):
attrs_after = [attrs_after]
attrs_after = list_diff(attrs_after, [key, fk_ltable, fk_rtable])
attrs_after.reverse()
col_pos = len(table.columns)
for a in attrs_after:
table.insert(col_pos, a, candset[a])
col_pos += 1
# reset the index
table.reset_index(inplace=True, drop=True)
# # update the catalog
cm.init_properties(table)
cm.copy_properties(candset, table)
return table
def sample_table(table, sample_size, replace=False, verbose=False):
"""
Sample a pandas DataFrame (for labeling purposes).
This function samples a DataFrame, typically used for labeling
purposes. This function expects the input DataFrame containing the
metadata of a candidate set (such as key, fk_ltable, fk_rtable, ltable,
rtable). Specifically, this function creates a copy of the input
DataFrame, samples the data using uniform random sampling (uses 'random'
function from numpy to sample) and returns the sampled DataFrame.
Further, also copies the properties from the input DataFrame to the output
DataFrame.
Args:
table (DataFrame): Input DataFrame to be sampled. Specifically,
a DataFrame containing the metadata of a candidate set (such as
key, fk_ltable, fk_rtable, ltable, rtable) in the catalog.
sample_size (int): Number of samples to be picked up from the input
DataFrame.
replace (boolean): Flag to indicate whether sampling should be done
with replacement or not (default value is False).
verbose (boolean): Flag to indicate whether more detailed information
about the execution steps should be printed out (default value is
False).
Returns:
A new DataFrame with 'sample_size' number of rows. Further,
this function sets the output DataFrame's properties same as input
DataFrame.
Raises:
AssertionError: If the input table is not of type pandas DataFrame.
AssertionError: If the input DataFrame size is 0.
AssertionError: If the sample_size is greater than the input
DataFrame size.
Notes:
As mentioned in the above description, the output DataFrame is
updated (in the catalog) with the properties from the input
DataFrame. A subtle point to note here is, when the replace flag is
set to True, then the output DataFrame can contain duplicate keys.
In that case, this function will not set the key and it is up to
the user to fix it after the function returns.
"""
# Validate input parameters.
# # The input DataFrame is expected to be of type pandas DataFrame.
if not isinstance(table, pd.DataFrame):
logger.error('Input table is not of type pandas dataframe')
raise AssertionError('Input table is not of type pandas dataframe')
# # There should at least not-zero rows to sample from
if len(table) == 0:
logger.error('Size of the input table is 0')
raise AssertionError('Size of the input table is 0')
# # The sample size should be less than or equal to the number of rows in
# the input DataFrame
if len(table) < sample_size:
logger.error('Sample size is larger than the input table size')
raise AssertionError('Sample size is larger than the input table size')
# Now, validate the metadata for the input DataFrame as we have to copy
# these properties to the output DataFrame
# # First, display what metadata is required for this function
ch.log_info(
logger, 'Required metadata: cand.set key, fk ltable, '
'fk rtable, ltable, rtable, ltable key, rtable key', verbose)
# # Second, get the metadata
key, fk_ltable, fk_rtable, ltable, rtable, l_key, r_key = \
cm.get_metadata_for_candset(table, logger, verbose)
# # Third, validate the metadata
cm.validate_metadata_for_candset(table, key, fk_ltable, fk_rtable, ltable,
rtable, l_key, r_key, logger, verbose)
# Get the sample set for the output table
sample_indices = pd.np.random.choice(len(table),
sample_size,
replace=replace)
# Sort the indices ordered by index value
sample_indices = sorted(sample_indices)
sampled_table = table.iloc[list(sample_indices)]
# Copy the properties
cm.init_properties(sampled_table)
# # If the replace is set to True, then we should check for the validity
# of key before setting it
if replace:
properties = cm.get_all_properties(table)
for property_name, property_value in six.iteritems(properties):
if property_name == 'key':
# Check for the validity of key before setting it
cm.set_key(sampled_table, property_value)
else:
# Copy the other properties as is
cm.set_property(sampled_table, property_name, property_value)
else:
cm.copy_properties(table, sampled_table)
# Return the sampled table
return sampled_table
def test_copy_properties_invalid_tar_df(self):
A = read_csv_metadata(path_a)
cm.copy_properties(A, None)
def test_copy_properties_invalid_src_df(self):
A = read_csv_metadata(path_a)
cm.copy_properties(None, A)
def sample_table(table, sample_size, replace=False, verbose=False):
"""
Sample a pandas DataFrame (for labeling purposes).
This function samples a DataFrame, typically used for labeling
purposes. This function expects the input DataFrame containing the
metadata of a candidate set (such as key, fk_ltable, fk_rtable, ltable,
rtable). Specifically, this function creates a copy of the input
DataFrame, samples the data using uniform random sampling (uses 'random'
function from numpy to sample) and returns the sampled DataFrame.
Further, also copies the properties from the input DataFrame to the output
DataFrame.
Args:
table (DataFrame): Input DataFrame to be sampled. Specifically,
a DataFrame containing the metadata of a candidate set (such as
key, fk_ltable, fk_rtable, ltable, rtable) in the catalog.
sample_size (int): Number of samples to be picked up from the input
DataFrame.
replace (boolean): Flag to indicate whether sampling should be done
with replacement or not (default value is False).
verbose (boolean): Flag to indicate whether more detailed information
about the execution steps should be printed out (default value is
False).
Returns:
A new DataFrame with 'sample_size' number of rows. Further,
this function sets the output DataFrame's properties same as input
DataFrame.
Raises:
AssertionError: If the input table is not of type pandas DataFrame.
AssertionError: If the input DataFrame size is 0.
AssertionError: If the sample_size is greater than the input
DataFrame size.
Notes:
As mentioned in the above description, the output DataFrame is
updated (in the catalog) with the properties from the input
DataFrame. A subtle point to note here is, when the replace flag is
set to True, then the output DataFrame can contain duplicate keys.
In that case, this function will not set the key and it is up to
the user to fix it after the function returns.
"""
# Validate input parameters.
# # The input DataFrame is expected to be of type pandas DataFrame.
if not isinstance(table, pd.DataFrame):
logger.error('Input table is not of type pandas dataframe')
raise AssertionError('Input table is not of type pandas dataframe')
# # There should at least not-zero rows to sample from
if len(table) == 0:
logger.error('Size of the input table is 0')
raise AssertionError('Size of the input table is 0')
# # The sample size should be less than or equal to the number of rows in
# the input DataFrame
if len(table) < sample_size:
logger.error('Sample size is larger than the input table size')
raise AssertionError('Sample size is larger than the input table size')
# Now, validate the metadata for the input DataFrame as we have to copy
# these properties to the output DataFrame
# # First, display what metadata is required for this function
ch.log_info(logger, 'Required metadata: cand.set key, fk ltable, '
'fk rtable, ltable, rtable, ltable key, rtable key',
verbose)
# # Second, get the metadata
key, fk_ltable, fk_rtable, ltable, rtable, l_key, r_key = \
cm.get_metadata_for_candset(table, logger, verbose)
# # Third, validate the metadata
cm.validate_metadata_for_candset(table, key, fk_ltable, fk_rtable,
ltable, rtable, l_key, r_key,
logger, verbose)
# Get the sample set for the output table
sample_indices = pd.np.random.choice(len(table), sample_size,
replace=replace)
# Sort the indices ordered by index value
sample_indices = sorted(sample_indices)
sampled_table = table.iloc[list(sample_indices)]
# Copy the properties
cm.init_properties(sampled_table)
# # If the replace is set to True, then we should check for the validity
# of key before setting it
if replace:
properties = cm.get_all_properties(table)
for property_name, property_value in six.iteritems(properties):
if property_name == 'key':
# Check for the validity of key before setting it
cm.set_key(sampled_table, property_value)
else:
# Copy the other properties as is
cm.set_property(sampled_table, property_name, property_value)
else:
cm.copy_properties(table, sampled_table)
# Return the sampled table
return sampled_table
def test_copy_properties_update_false_1(self):
A = read_csv_metadata(path_a)
A1 = read_csv_metadata(path_a)
status=cm.copy_properties(A, A1, update=False)
self.assertEqual(status, False)
def test_copy_properties_src_df_notin_catalog(self):
A = pd.read_csv(path_a)
A1 = pd.read_csv(path_a)
cm.copy_properties(A, A1)