generalized keyword argument handling for:

Clustering.py, CorrelationTest.py, KNN.py, NaiveBayes.py
This commit is contained in:
Arthur Lu 2022-02-08 07:29:47 +00:00
parent 237e69b732
commit 44569c9fcf
4 changed files with 40 additions and 32 deletions

View File

@ -4,10 +4,12 @@
# this should be imported as a python module using 'from tra_analysis import Clustering'
# setup:
__version__ = "2.0.1"
__version__ = "2.0.2"
# changelog should be viewed using print(analysis.__changelog__)
__changelog__ = """changelog:
2.0.2:
- generalized optional args to **kwargs
2.0.1:
- added normalization preprocessing to clustering, expects instance of sklearn.preprocessing.Normalizer()
2.0.0:
@ -30,32 +32,32 @@ __all__ = [
import sklearn
def kmeans(data, normalizer = None, n_clusters=8, init="k-means++", n_init=10, max_iter=300, tol=0.0001, precompute_distances="auto", verbose=0, random_state=None, copy_x=True, n_jobs=None, algorithm="auto"):
def kmeans(data, normalizer = None, **kwargs):
if normalizer != None:
data = normalizer.transform(data)
kernel = sklearn.cluster.KMeans(n_clusters = n_clusters, init = init, n_init = n_init, max_iter = max_iter, tol = tol, precompute_distances = precompute_distances, verbose = verbose, random_state = random_state, copy_x = copy_x, n_jobs = n_jobs, algorithm = algorithm)
kernel = sklearn.cluster.KMeans(**kwargs)
kernel.fit(data)
predictions = kernel.predict(data)
centers = kernel.cluster_centers_
return centers, predictions
def dbscan(data, normalizer=None, eps=0.5, min_samples=5, metric='euclidean', metric_params=None, algorithm='auto', leaf_size=30, p=None, n_jobs=None):
def dbscan(data, normalizer=None, **kwargs):
if normalizer != None:
data = normalizer.transform(data)
model = sklearn.cluster.DBSCAN(eps = eps, min_samples = min_samples, metric = metric, metric_params = metric_params, algorithm = algorithm, leaf_size = leaf_size, p = p, n_jobs = n_jobs).fit(data)
model = sklearn.cluster.DBSCAN(**kwargs).fit(data)
return model.labels_
def spectral(data, normalizer=None, n_clusters=8, eigen_solver=None, n_components=None, random_state=None, n_init=10, gamma=1.0, affinity='rbf', n_neighbors=10, eigen_tol=0.0, assign_labels='kmeans', degree=3, coef0=1, kernel_params=None, n_jobs=None, verbose=False):
def spectral(data, normalizer=None, **kwargs):
if normalizer != None:
data = normalizer.transform(data)
model = sklearn.cluster.SpectralClustering(n_clusters = n_clusters, eigen_solver = eigen_solver, n_components = n_components, random_state = random_state, n_init = n_init, gamma = gamma, affinity = affinity, n_neighbors = n_neighbors, eigen_tol = eigen_tol, assign_labels = assign_labels, degree = degree, coef0 = coef0, kernel_params = kernel_params, n_jobs = n_jobs).fit(data)
model = sklearn.cluster.SpectralClustering(**kwargs).fit(data)
return model.labels_

View File

@ -4,9 +4,11 @@
# this should be imported as a python module using 'from tra_analysis import CorrelationTest'
# setup:
__version__ = "1.0.2"
__version__ = "1.0.3"
__changelog__ = """changelog:
1.0.3:
- generalized optional args to **kwargs
1.0.2:
- optimized imports
1.0.1:
@ -42,9 +44,9 @@ def pearson(x, y):
results = scipy.stats.pearsonr(x, y)
return {"r-value": results[0], "p-value": results[1]}
def spearman(a, b = None, axis = 0, nan_policy = 'propagate'):
def spearman(a, b = None, **kwargs):
results = scipy.stats.spearmanr(a, b = b, axis = axis, nan_policy = nan_policy)
results = scipy.stats.spearmanr(a, b = b, **kwargs)
return {"r-value": results[0], "p-value": results[1]}
def point_biserial(x, y):
@ -52,17 +54,17 @@ def point_biserial(x, y):
results = scipy.stats.pointbiserialr(x, y)
return {"r-value": results[0], "p-value": results[1]}
def kendall(x, y, initial_lexsort = None, nan_policy = 'propagate', method = 'auto'):
def kendall(x, y, **kwargs):
results = scipy.stats.kendalltau(x, y, initial_lexsort = initial_lexsort, nan_policy = nan_policy, method = method)
results = scipy.stats.kendalltau(x, y, **kwargs)
return {"tau": results[0], "p-value": results[1]}
def kendall_weighted(x, y, rank = True, weigher = None, additive = True):
def kendall_weighted(x, y, **kwargs):
results = scipy.stats.weightedtau(x, y, rank = rank, weigher = weigher, additive = additive)
results = scipy.stats.weightedtau(x, y, **kwargs)
return {"tau": results[0], "p-value": results[1]}
def mgc(x, y, compute_distance = None, reps = 1000, workers = 1, is_twosamp = False, random_state = None):
def mgc(x, y, **kwargs):
results = scipy.stats.multiscale_graphcorr(x, y, compute_distance = compute_distance, reps = reps, workers = workers, is_twosamp = is_twosamp, random_state = random_state)
results = scipy.stats.multiscale_graphcorr(x, y, **kwargs)
return {"k-value": results[0], "p-value": results[1], "data": results[2]} # unsure if MGC test returns a k value

View File

@ -4,9 +4,11 @@
# this should be imported as a python module using 'from tra_analysis import KNN'
# setup:
__version__ = "1.0.1"
__version__ = "1.0.2"
__changelog__ = """changelog:
1.0.2:
- generalized optional args to **kwargs
1.0.1:
- optimized imports
1.0.0:
@ -27,19 +29,19 @@ __all__ = [
import sklearn
from . import ClassificationMetric, RegressionMetric
def knn_classifier(data, labels, n_neighbors = 5, test_size = 0.3, algorithm='auto', leaf_size=30, metric='minkowski', metric_params=None, n_jobs=None, p=2, weights='uniform'): #expects *2d data and 1d labels post-scaling
def knn_classifier(data, labels, n_neighbors = 5, test_size = 0.3, **kwargs): #expects *2d data and 1d labels post-scaling
data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1)
model = sklearn.neighbors.KNeighborsClassifier(n_neighbors = n_neighbors, weights = weights, algorithm = algorithm, leaf_size = leaf_size, p = p, metric = metric, metric_params = metric_params, n_jobs = n_jobs)
model = sklearn.neighbors.KNeighborsClassifier(n_neighbors = n_neighbors, **kwargs)
model.fit(data_train, labels_train)
predictions = model.predict(data_test)
return model, ClassificationMetric(predictions, labels_test)
def knn_regressor(data, outputs, n_neighbors = 5, test_size = 0.3, weights = "uniform", algorithm = "auto", leaf_size = 30, p = 2, metric = "minkowski", metric_params = None, n_jobs = None):
def knn_regressor(data, outputs, n_neighbors = 5, test_size = 0.3, **kwargs):
data_train, data_test, outputs_train, outputs_test = sklearn.model_selection.train_test_split(data, outputs, test_size=test_size, random_state=1)
model = sklearn.neighbors.KNeighborsRegressor(n_neighbors = n_neighbors, weights = weights, algorithm = algorithm, leaf_size = leaf_size, p = p, metric = metric, metric_params = metric_params, n_jobs = n_jobs)
model = sklearn.neighbors.KNeighborsRegressor(n_neighbors = n_neighbors, **kwargs)
model.fit(data_train, outputs_train)
predictions = model.predict(data_test)

View File

@ -4,9 +4,11 @@
# this should be imported as a python module using 'from tra_analysis import NaiveBayes'
# setup:
__version__ = "1.0.1"
__version__ = "1.0.2"
__changelog__ = """changelog:
1.0.2:
- generalized optional args to **kwargs
1.0.1:
- optimized imports
1.0.0:
@ -20,45 +22,45 @@ __author__ = (
__all__ = [
'gaussian',
'multinomial'
'multinomial',
'bernoulli',
'complement'
'complement',
]
import sklearn
from . import ClassificationMetric
def gaussian(data, labels, test_size = 0.3, priors = None, var_smoothing = 1e-09):
def gaussian(data, labels, test_size = 0.3, **kwargs):
data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1)
model = sklearn.naive_bayes.GaussianNB(priors = priors, var_smoothing = var_smoothing)
model = sklearn.naive_bayes.GaussianNB(**kwargs)
model.fit(data_train, labels_train)
predictions = model.predict(data_test)
return model, ClassificationMetric(predictions, labels_test)
def multinomial(data, labels, test_size = 0.3, alpha=1.0, fit_prior=True, class_prior=None):
def multinomial(data, labels, test_size = 0.3, **kwargs):
data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1)
model = sklearn.naive_bayes.MultinomialNB(alpha = alpha, fit_prior = fit_prior, class_prior = class_prior)
model = sklearn.naive_bayes.MultinomialNB(**kwargs)
model.fit(data_train, labels_train)
predictions = model.predict(data_test)
return model, ClassificationMetric(predictions, labels_test)
def bernoulli(data, labels, test_size = 0.3, alpha=1.0, binarize=0.0, fit_prior=True, class_prior=None):
def bernoulli(data, labels, test_size = 0.3, **kwargs):
data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1)
model = sklearn.naive_bayes.BernoulliNB(alpha = alpha, binarize = binarize, fit_prior = fit_prior, class_prior = class_prior)
model = sklearn.naive_bayes.BernoulliNB(**kwargs)
model.fit(data_train, labels_train)
predictions = model.predict(data_test)
return model, ClassificationMetric(predictions, labels_test)
def complement(data, labels, test_size = 0.3, alpha=1.0, fit_prior=True, class_prior=None, norm=False):
def complement(data, labels, test_size = 0.3, **kwargs):
data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1)
model = sklearn.naive_bayes.ComplementNB(alpha = alpha, fit_prior = fit_prior, class_prior = class_prior, norm = norm)
model = sklearn.naive_bayes.ComplementNB(**kwargs)
model.fit(data_train, labels_train)
predictions = model.predict(data_test)