fixed/optimized imports,

fixed headers

Signed-off-by: Arthur Lu <learthurgo@gmail.com>

analysis-master/tra_analysis/Analysis.py

@@ -7,10 +7,13 @@
 #    current benchmark of optimization: 1.33 times faster
 # setup:
 
-__version__ = "3.0.4"
+__version__ = "3.0.5"
 
 # changelog should be viewed using print(analysis.__changelog__)
 __changelog__ = """changelog:
+	3.0.5:
+		- removed extra submodule imports
+		- fixed/optimized header
 	3.0.4:
 		- removed -_obj imports
 	3.0.3:
@@ -361,7 +364,6 @@ __all__ = [
 	'histo_analysis',
 	'regression',
 	'Metric',
-	'kmeans',
 	'pca',
 	'decisiontree',
 	# all statistics functions left out due to integration in other functions
@@ -374,21 +376,14 @@ __all__ = [
 import csv
 from tra_analysis.metrics import elo as Elo
 from tra_analysis.metrics import glicko2 as Glicko2
-import math
 import numpy as np
 import scipy
-from scipy import optimize, stats
-import sklearn
-from sklearn import preprocessing, pipeline, linear_model, metrics, cluster, decomposition, tree, neighbors, naive_bayes, svm, model_selection, ensemble
+import sklearn, sklearn.cluster
 from tra_analysis.metrics import trueskill as Trueskill
-import warnings
 
 # import submodules
 
-from .Array import Array
 from .ClassificationMetric import ClassificationMetric
-from .RegressionMetric import RegressionMetric
-from . import SVM
 
 class error(ValueError):
 	pass
@@ -599,16 +594,7 @@ def npmin(data):
 def npmax(data):
 
 	return np.amax(data)
-""" need to decide what to do with this function
-def kmeans(data, 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"):
 
-	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.fit(data)
-	predictions = kernel.predict(data)
-	centers = kernel.cluster_centers_
-
-	return centers, predictions
-"""
 def pca(data, n_components = None, copy = True, whiten = False, svd_solver = "auto", tol = 0.0, iterated_power = "auto", random_state = None):
 
 	kernel = sklearn.decomposition.PCA(n_components = n_components, copy = copy, whiten = whiten, svd_solver = svd_solver, tol = tol, iterated_power = iterated_power, random_state = random_state)

analysis-master/tra_analysis/ClassificationMetric.py

@@ -4,9 +4,11 @@
 #    this should be imported as a python module using 'from tra_analysis import ClassificationMetric'
 # setup:
 
-__version__ = "1.0.1"
+__version__ = "1.0.2"
 
 __changelog__ = """changelog:
+	1.0.2:
+		- optimized imports
 	1.0.1:
 		- fixed __all__
 	1.0.0:
@@ -22,7 +24,6 @@ __all__ = [
 ]
 
 import sklearn
-from sklearn import metrics
 
 class ClassificationMetric():
 

analysis-master/tra_analysis/CorrelationTest.py

@@ -4,9 +4,11 @@
 #    this should be imported as a python module using 'from tra_analysis import CorrelationTest'
 # setup:
 
-__version__ = "1.0.1"
+__version__ = "1.0.2"
 
 __changelog__ = """changelog:
+	1.0.2:
+		- optimized imports
 	1.0.1:
 		- fixed __all__
 	1.0.0:
@@ -29,7 +31,6 @@ __all__ = [
 ]
 
 import scipy
-from scipy import stats
 
 def anova_oneway(*args): #expects arrays of samples
 

analysis-master/tra_analysis/KNN.py

@@ -4,9 +4,11 @@
 #    this should be imported as a python module using 'from tra_analysis import KNN'
 # setup:
 
-__version__ = "1.0.0"
+__version__ = "1.0.1"
 
 __changelog__ = """changelog:
+	1.0.1:
+		- optimized imports
 	1.0.0:
 		- ported analysis.KNN() here
 		- removed classness
@@ -23,7 +25,6 @@ __all__ = [
 ]
 
 import sklearn
-from sklearn import model_selection, neighbors
 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

analysis-master/tra_analysis/NaiveBayes.py

@@ -4,9 +4,11 @@
 #    this should be imported as a python module using 'from tra_analysis import NaiveBayes'
 # setup:
 
-__version__ = "1.0.0"
+__version__ = "1.0.1"
 
 __changelog__ = """changelog:
+	1.0.1:
+		- optimized imports
 	1.0.0:
 		- ported analysis.NaiveBayes() here
 		- removed classness
@@ -24,8 +26,7 @@ __all__ = [
 ]
 
 import sklearn
-from sklearn import model_selection, naive_bayes
-from . import ClassificationMetric, RegressionMetric
+from . import ClassificationMetric
 
 def gaussian(data, labels, test_size = 0.3, priors = None, var_smoothing = 1e-09):
 

analysis-master/tra_analysis/RandomForest.py

@@ -4,9 +4,11 @@
 #    this should be imported as a python module using 'from tra_analysis import RandomForest'
 # setup:
 
-__version__ = "1.0.1"
+__version__ = "1.0.2"
 
 __changelog__ = """changelog:
+	1.0.2:
+		- optimized imports
 	1.0.1:
 		- fixed __all__
 	1.0.0:
@@ -23,8 +25,7 @@ __all__ = [
 	"random_forest_regressor",
 ]
 
-import sklearn
-from sklearn import ensemble, model_selection
+import sklearn, sklearn.ensemble, sklearn.naive_bayes
 from . import ClassificationMetric, RegressionMetric
 
 def random_forest_classifier(data, labels, test_size, n_estimators, criterion="gini", max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_features="auto", max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, bootstrap=True, oob_score=False, n_jobs=None, random_state=None, verbose=0, warm_start=False, class_weight=None):

analysis-master/tra_analysis/RegressionMetric.py

@@ -4,9 +4,11 @@
 #    this should be imported as a python module using 'from tra_analysis import RegressionMetric'
 # setup:
 
-__version__ = "1.0.0"
+__version__ = "1.0.1"
 
 __changelog__ = """changelog:
+	1.0.1:
+		- optimized imports
 	1.0.0:
 		- ported analysis.RegressionMetric() here
 """
@@ -21,7 +23,6 @@ __all__ = [
 
 import numpy as np
 import sklearn
-from sklearn import metrics
 
 class RegressionMetric():
 

analysis-master/tra_analysis/SVM.py

@@ -4,9 +4,11 @@
 #    this should be imported as a python module using 'from tra_analysis import SVM'
 # setup:
 
-__version__ = "1.0.2"
+__version__ = "1.0.3"
 
 __changelog__ = """changelog:
+	1.0.3:
+		- optimized imports
 	1.0.2: 
 		- fixed __all__
 	1.0.1:
@@ -30,7 +32,6 @@ __all__ = [
 ]
 
 import sklearn
-from sklearn import svm
 from . import ClassificationMetric, RegressionMetric
 
 class CustomKernel:

analysis-master/tra_analysis/Sort.py

@@ -16,7 +16,7 @@ __changelog__ = """changelog:
 
 __author__ = (
 	"Arthur Lu <learthurgo@gmail.com>",
-	"James Pan <zpan@imsa.edu>"
+	"James Pan <zpan@imsa.edu>",
 )
 
 __all__ = [

analysis-master/tra_analysis/StatisticalTest.py

@@ -4,9 +4,11 @@
 #    this should be imported as a python module using 'from tra_analysis import StatisticalTest'
 # setup:
 
-__version__ = "1.0.2"
+__version__ = "1.0.3"
 
 __changelog__ = """changelog:
+	1.0.3:
+		- optimized imports
 	1.0.2:
 		- added tukey_multicomparison
 		- fixed styling
@@ -61,7 +63,6 @@ __all__ = [
 
 import numpy as np
 import scipy
-from scipy import stats, interpolate
 
 def ttest_onesample(a, popmean, axis = 0, nan_policy = 'propagate'):
 
@@ -279,9 +280,9 @@ def get_tukeyQcrit(k, df, alpha=0.05):
 	cv001 = c[:, 2::2]
 
 	if alpha == 0.05:
-		intp = interpolate.interp1d(crows, cv005[:,k-2])
+		intp = scipy.interpolate.interp1d(crows, cv005[:,k-2])
 	elif alpha == 0.01:
-		intp = interpolate.interp1d(crows, cv001[:,k-2])
+		intp = scipy.interpolate.interp1d(crows, cv001[:,k-2])
 	else:
 		raise ValueError('only implemented for alpha equal to 0.01 and 0.05')
 	return intp(df)

analysis-master/tra_analysis/__init__.py

@@ -16,6 +16,8 @@ __changelog__ = """changelog:
 		- deprecated titanlearn.py
 		- deprecated visualization.py
 		- removed matplotlib from requirements
+		- removed extra submodule imports in Analysis
+		- added typehinting, docstrings for each function
 	3.0.0:
 		- incremented version to release 3.0.0
 	3.0.0-rc2:
@@ -45,6 +47,7 @@ __all__ = [
 	"Analysis",
 	"Array",
 	"ClassificationMetric",
+	"Clustering",
 	"CorrelationTest",
 	"Expression",
 	"Fit",