def test_load_csv():
csv = loader.load_csv('boat.csv')
assert csv is None
csv = loader.load_csv('data/boat.csv')
assert csv.shape == (100, 4)
def _load(self, file_path):
"""Loads and parses a dataframe from a file.
Args:
file_path (str): File to be loaded.
Returns:
Arrays holding the features and labels.
"""
# Getting file extension
extension = file_path.split('.')[-1]
if extension == 'csv':
data = loader.load_csv(file_path)
elif extension == 'txt':
data = loader.load_txt(file_path)
elif extension == 'json':
data = loader.load_json(file_path)
else:
raise e.ArgumentError(
'File extension not recognized. It should be `.csv`, `.json` or `.txt`'
)
X, Y = p.parse_loader(data)
return X, Y
def _read_distances(self, file_name):
"""Reads the distance between nodes from a pre-defined file.
Args:
file_name (str): File to be loaded.
"""
logger.debug('Running private method: read_distances().')
# Getting file extension
extension = file_name.split('.')[-1]
if extension == 'csv':
distances = loader.load_csv(file_name)
elif extension == 'txt':
distances = loader.load_txt(file_name)
else:
# Raises an ArgumentError exception
raise e.ArgumentError('File extension not recognized. It should be either `.csv` or .txt`')
# Check if distances have been properly loaded
if distances is None:
raise e.ValueError('Pre-computed distances could not been properly loaded')
# Apply the distances matrix to the property
self.pre_distances = distances
def test_parse_loader():
X, Y = parser.parse_loader([])
assert X is None
assert Y is None
try:
data = np.ones((4, 4))
X, Y = parser.parse_loader(data)
except:
try:
data = np.ones((4, 4))
data[3, 1] = 3
X, Y = parser.parse_loader(data)
except:
csv = loader.load_csv('data/boat.csv')
X, Y = parser.parse_loader(csv)
assert X.shape == (100, 2)
assert Y.shape == (100, )
def _load(self, file_path):
"""Loads and parses a dataframe from a file.
Args:
file_path (str): File to be loaded.
Returns:
Arrays holding the features and labels.
"""
# Getting file extension
extension = file_path.split('.')[-1]
# Check if extension is .csv
if extension == 'csv':
# If yes, call the method that actually loads csv
data = loader.load_csv(file_path)
# Check if extension is .txt
elif extension == 'txt':
# If yes, call the method that actually loads txt
data = loader.load_txt(file_path)
# Check if extension is .json
elif extension == 'json':
# If yes, call the method that actually loads json
data = loader.load_json(file_path)
# If extension is not recognized
else:
# Raises an ArgumentError exception
raise e.ArgumentError(
'File extension not recognized. It should be `.csv`, `.json` or `.txt`'
)
# Parsing array
X, Y = p.parse_loader(data)
return X, Y
def _read_distances(self, file_path):
"""Reads the distance between nodes from a pre-defined file.
Args:
file_path (str): File to be loaded.
Returns:
A matrix with pre-computed distances.
"""
logger.debug('Running private method: read_distances().')
# Getting file extension
extension = file_path.split('.')[-1]
# Check if extension is .csv
if extension == 'csv':
# If yes, call the method that actually loads csv
distances = loader.load_csv(file_path)
# Check if extension is .txt
elif extension == 'txt':
# If yes, call the method that actually loads txt
distances = loader.load_txt(file_path)
# If extension is not recognized
else:
# Raises an ArgumentError exception
raise e.ArgumentError(
'File extension not recognized. It should be either `.csv` or .txt`'
)
# Check if distances have been properly loaded
if distances is None:
# If not, raises a ValueError
raise e.ValueError(
'Pre-computed distances could not been properly loaded')
return distances
import numpy as np
import pytest
from opfython.math import distance
from opfython.stream import loader, parser
from opfython.subgraphs import knn
csv = loader.load_csv('data/boat.csv')
X, Y = parser.parse_loader(csv)
def test_knn_subgraph_n_clusters():
subgraph = knn.KNNSubgraph(X, Y)
assert subgraph.n_clusters == 0
def test_knn_subgraph_n_clusters_setter():
subgraph = knn.KNNSubgraph(X, Y)
try:
subgraph.n_clusters = 0.5
except:
subgraph.n_clusters = 1
assert subgraph.n_clusters == 1
try:
subgraph.n_clusters = -1
except:
subgraph.n_clusters = 1
import opfython.stream.loader as l
# Loading a .csv file
csv = l.load_csv('data/sample.csv')
# Loading a .txt file
txt = l.load_txt('data/sample.txt')
# Loading a .json file
json = l.load_json('data/sample.json')
import opfython.stream.loader as l
# Loading a .csv file
csv = l.load_csv('data/boat.csv')
# Loading a .txt file
txt = l.load_txt('data/boat.txt')
# Loading a .json file
json = l.load_json('data/boat.json')
