alu/tra-analysis
1
0
Fork 0
mirror of https://github.com/titanscouting/tra-analysis.git synced 2024-09-20 08:57:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

Analysis.py v 3.0.1

Browse Source 
Signed-off-by: Arthur Lu <learthurgo@gmail.com>
This commit is contained in:
Arthur Lu 2020-10-14 18:47:44 +00:00
parent 57fa659f90
commit de0791a7fd
2 changed files with 3 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
analysis-master/requirements.txt
View File

@ -1,4 +1,3 @@
numba
numpy numpy
scipy scipy
scikit-learn scikit-learn

19
analysis-master/tra_analysis/Analysis.py
View File

@ -7,10 +7,12 @@
# current benchmark of optimization: 1.33 times faster # current benchmark of optimization: 1.33 times faster
# setup: # setup:
__version__ = "3.0.0" __version__ = "3.0.1"
# changelog should be viewed using print(analysis.__changelog__) # changelog should be viewed using print(analysis.__changelog__)
__changelog__ = """changelog: __changelog__ = """changelog:
3.0.1:
- removed numba dependency and calls
3.0.0: 3.0.0:
- exported several submodules to their own files while preserving backwards compatibility: - exported several submodules to their own files while preserving backwards compatibility:
- Array - Array
@ -376,8 +378,6 @@ import csv
from tra_analysis.metrics import elo as Elo from tra_analysis.metrics import elo as Elo
from tra_analysis.metrics import glicko2 as Glicko2 from tra_analysis.metrics import glicko2 as Glicko2
import math import math
import numba
from numba import jit
import numpy as np import numpy as np
import scipy import scipy
from scipy import optimize, stats from scipy import optimize, stats
@ -409,7 +409,6 @@ def load_csv(filepath):
return file_array return file_array
# expects 1d array # expects 1d array
@jit(forceobj=True)
def basic_stats(data): def basic_stats(data):
data_t = np.array(data).astype(float) data_t = np.array(data).astype(float)
@ -424,14 +423,12 @@ def basic_stats(data):
return {"mean": _mean, "median": _median, "standard-deviation": _stdev, "variance": _variance, "minimum": _min, "maximum": _max} return {"mean": _mean, "median": _median, "standard-deviation": _stdev, "variance": _variance, "minimum": _min, "maximum": _max}
# returns z score with inputs of point, mean and standard deviation of spread # returns z score with inputs of point, mean and standard deviation of spread
@jit(forceobj=True)
def z_score(point, mean, stdev): def z_score(point, mean, stdev):
score = (point - mean) / stdev score = (point - mean) / stdev
return score return score
# expects 2d array, normalizes across all axes # expects 2d array, normalizes across all axes
@jit(forceobj=True)
def z_normalize(array, *args): def z_normalize(array, *args):
array = np.array(array) array = np.array(array)
@ -440,7 +437,6 @@ def z_normalize(array, *args):
return array return array
@jit(forceobj=True)
# expects 2d array of [x,y] # expects 2d array of [x,y]
def histo_analysis(hist_data): def histo_analysis(hist_data):
@ -589,37 +585,30 @@ class Metric:
return Trueskill.rate(team_ratings, ranks=observations) return Trueskill.rate(team_ratings, ranks=observations)
@jit(nopython=True)
def mean(data): def mean(data):
return np.mean(data) return np.mean(data)
@jit(nopython=True)
def median(data): def median(data):
return np.median(data) return np.median(data)
@jit(nopython=True)
def stdev(data): def stdev(data):
return np.std(data) return np.std(data)
@jit(nopython=True)
def variance(data): def variance(data):
return np.var(data) return np.var(data)
@jit(nopython=True)
def npmin(data): def npmin(data):
return np.amin(data) return np.amin(data)
@jit(nopython=True)
def npmax(data): def npmax(data):
return np.amax(data) return np.amax(data)
@jit(forceobj=True)
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"): 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 = 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)
@ -629,14 +618,12 @@ def kmeans(data, n_clusters=8, init="k-means++", n_init=10, max_iter=300, tol=0.
return centers, predictions return centers, predictions
@jit(forceobj=True)
def pca(data, n_components = None, copy = True, whiten = False, svd_solver = "auto", tol = 0.0, iterated_power = "auto", random_state = None): 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) 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)
return kernel.fit_transform(data) return kernel.fit_transform(data)
@jit(forceobj=True)
def decisiontree(data, labels, test_size = 0.3, criterion = "gini", splitter = "default", max_depth = None): #expects *2d data and 1d labels def decisiontree(data, labels, test_size = 0.3, criterion = "gini", splitter = "default", max_depth = None): #expects *2d data and 1d labels
data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1) data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1)