mirror of
https://github.com/titanscouting/tra-analysis.git
synced 2024-12-27 09:59:10 +00:00
started c-ifying analysis
This commit is contained in:
ltcptgeneral
parent
0d240e3b09
commit
087e201baa
@ -1,15 +1,15 @@
|
||||
#Titan Robotics Team 2022: Data Analysis Module
|
||||
#Written by Arthur Lu & Jacob Levine
|
||||
#Notes:
|
||||
# Titan Robotics Team 2022: Data Analysis Module
|
||||
# Written by Arthur Lu & Jacob Levine
|
||||
# Notes:
|
||||
# this should be imported as a python module using 'import analysis'
|
||||
# this should be included in the local directory or environment variable
|
||||
# this module has not been optimized for multhreaded computing
|
||||
#number of easter eggs: 2
|
||||
#setup:
|
||||
# number of easter eggs: 2
|
||||
# setup:
|
||||
|
||||
__version__ = "1.0.8.005"
|
||||
|
||||
#changelog should be viewed using print(analysis.__changelog__)
|
||||
# changelog should be viewed using print(analysis.__changelog__)
|
||||
__changelog__ = """changelog:
|
||||
1.0.8.005:
|
||||
- minor fixes
|
||||
@ -101,7 +101,7 @@ __changelog__ = """changelog:
|
||||
__author__ = (
|
||||
"Arthur Lu <arthurlu@ttic.edu>, "
|
||||
"Jacob Levine <jlevine@ttic.edu>,"
|
||||
)
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
'_init_device',
|
||||
@ -125,12 +125,12 @@ __all__ = [
|
||||
'optimize_regression',
|
||||
'select_best_regression',
|
||||
'basic_analysis',
|
||||
#all statistics functions left out due to integration in other functions
|
||||
]
|
||||
# all statistics functions left out due to integration in other functions
|
||||
]
|
||||
|
||||
#now back to your regularly scheduled programming:
|
||||
# now back to your regularly scheduled programming:
|
||||
|
||||
#imports (now in alphabetical order! v 1.0.3.006):
|
||||
# imports (now in alphabetical order! v 1.0.3.006):
|
||||
|
||||
from bisect import bisect_left, bisect_right
|
||||
import collections
|
||||
@ -149,14 +149,16 @@ import scipy
|
||||
from scipy.optimize import curve_fit
|
||||
from scipy import stats
|
||||
from sklearn import *
|
||||
#import statistics <-- statistics.py functions have been integrated into analysis.py as of v 1.0.3.002
|
||||
# import statistics <-- statistics.py functions have been integrated into analysis.py as of v 1.0.3.002
|
||||
import time
|
||||
import torch
|
||||
|
||||
|
||||
class error(ValueError):
|
||||
pass
|
||||
|
||||
def _init_device (setting, arg): #initiates computation device for ANNs
|
||||
|
||||
def _init_device(setting, arg): # initiates computation device for ANNs
|
||||
if setting == "cuda":
|
||||
try:
|
||||
return torch.device(setting + ":" + str(arg) if torch.cuda.is_available() else "cpu")
|
||||
@ -170,6 +172,7 @@ def _init_device (setting, arg): #initiates computation device for ANNs
|
||||
else:
|
||||
raise error("specified device does not exist")
|
||||
|
||||
|
||||
class c_entities:
|
||||
|
||||
c_names = []
|
||||
@ -190,7 +193,6 @@ class c_entities:
|
||||
self.c_logic = logic
|
||||
return None
|
||||
|
||||
|
||||
def append(self, n_name, n_id, n_pos, n_property, n_logic):
|
||||
self.c_names.append(n_name)
|
||||
self.c_ids.append(n_id)
|
||||
@ -232,6 +234,7 @@ class c_entities:
|
||||
def regurgitate(self):
|
||||
return[self.c_names, self.c_ids, self.c_pos, self.c_properties, self.c_logic]
|
||||
|
||||
|
||||
class nc_entities:
|
||||
|
||||
c_names = []
|
||||
@ -241,7 +244,7 @@ class nc_entities:
|
||||
c_effects = []
|
||||
|
||||
def debug(self):
|
||||
print ("nc_entities (non-controlable entities) has attributes names, ids, positions, properties, and effects. __init__ takes self, 1d array of names, 1d array of ids, 2d array of positions, 2d array of properties, and 2d array of effects.")
|
||||
print("nc_entities (non-controlable entities) has attributes names, ids, positions, properties, and effects. __init__ takes self, 1d array of names, 1d array of ids, 2d array of positions, 2d array of properties, and 2d array of effects.")
|
||||
return[self.c_names, self.c_ids, self.c_pos, self.c_properties, self.c_effects]
|
||||
|
||||
def __init__(self, names, ids, pos, properties, effects):
|
||||
@ -295,6 +298,7 @@ class nc_entities:
|
||||
|
||||
return[self.c_names, self.c_ids, self.c_pos, self.c_properties, self.c_effects]
|
||||
|
||||
|
||||
class obstacles:
|
||||
|
||||
c_names = []
|
||||
@ -351,6 +355,7 @@ class obstacles:
|
||||
def regurgitate(self):
|
||||
return[self.c_names, self.c_ids, self.c_perim, self.c_effects]
|
||||
|
||||
|
||||
class objectives:
|
||||
|
||||
c_names = []
|
||||
@ -408,13 +413,16 @@ class objectives:
|
||||
def regurgitate(self):
|
||||
return[self.c_names, self.c_ids, self.c_pos, self.c_effects]
|
||||
|
||||
|
||||
def load_csv(filepath):
|
||||
with open(filepath, newline = '') as csvfile:
|
||||
with open(filepath, newline='') as csvfile:
|
||||
file_array = list(csv.reader(csvfile))
|
||||
csvfile.close()
|
||||
return file_array
|
||||
|
||||
def basic_stats(data, method, arg): # data=array, mode = ['1d':1d_basic_stats, 'column':c_basic_stats, 'row':r_basic_stats], arg for mode 1 or mode 2 for column or row
|
||||
|
||||
# data=array, mode = ['1d':1d_basic_stats, 'column':c_basic_stats, 'row':r_basic_stats], arg for mode 1 or mode 2 for column or row
|
||||
def basic_stats(data, method, arg):
|
||||
|
||||
if method == 'debug':
|
||||
return "basic_stats requires 3 args: data, mode, arg; where data is data to be analyzed, mode is an int from 0 - 2 depending on type of analysis (by column or by row) and is only applicable to 2d arrays (for 1d arrays use mode 1), and arg is row/column number for mode 1 or mode 2; function returns: [mean, median, mode, stdev, variance]"
|
||||
@ -423,7 +431,7 @@ def basic_stats(data, method, arg): # data=array, mode = ['1d':1d_basic_stats, '
|
||||
|
||||
data_t = []
|
||||
|
||||
for i in range (0, len(data), 1):
|
||||
for i in range(0, len(data), 1):
|
||||
data_t.append(float(data[i]))
|
||||
|
||||
_mean = mean(data_t)
|
||||
@ -498,64 +506,72 @@ def basic_stats(data, method, arg): # data=array, mode = ['1d':1d_basic_stats, '
|
||||
else:
|
||||
raise error("method error")
|
||||
|
||||
def z_score(point, mean, stdev): #returns z score with inputs of point, mean and standard deviation of spread
|
||||
score = (point - mean)/stdev
|
||||
|
||||
# returns z score with inputs of point, mean and standard deviation of spread
|
||||
def z_score(point, mean, stdev):
|
||||
score = (point - mean) / stdev
|
||||
return score
|
||||
|
||||
def z_normalize(x, y, mode): #mode is either 'x' or 'y' or 'both' depending on the variable(s) to be normalized
|
||||
|
||||
x_norm = []
|
||||
y_norm = []
|
||||
# mode is either 'x' or 'y' or 'both' depending on the variable(s) to be normalized
|
||||
def z_normalize(x, y, mode):
|
||||
|
||||
mean = 0
|
||||
stdev = 0
|
||||
x_norm = []
|
||||
y_norm = []
|
||||
|
||||
if mode == 'x':
|
||||
_mean, _median, _mode, _stdev, _variance = basic_stats(x, "1d", 0)
|
||||
mean = 0
|
||||
stdev = 0
|
||||
|
||||
for i in range (0, len(x), 1):
|
||||
x_norm.append(z_score(x[i], _mean, _stdev))
|
||||
if mode == 'x':
|
||||
_mean, _median, _mode, _stdev, _variance = basic_stats(x, "1d", 0)
|
||||
|
||||
return x_norm, y
|
||||
for i in range(0, len(x), 1):
|
||||
x_norm.append(z_score(x[i], _mean, _stdev))
|
||||
|
||||
if mode == 'y':
|
||||
_mean, _median, _mode, _stdev, _variance = basic_stats(y, "1d", 0)
|
||||
return x_norm, y
|
||||
|
||||
for i in range (0, len(y), 1):
|
||||
y_norm.append(z_score(y[i], _mean, _stdev))
|
||||
if mode == 'y':
|
||||
_mean, _median, _mode, _stdev, _variance = basic_stats(y, "1d", 0)
|
||||
|
||||
return x, y_norm
|
||||
for i in range(0, len(y), 1):
|
||||
y_norm.append(z_score(y[i], _mean, _stdev))
|
||||
|
||||
if mode == 'both':
|
||||
_mean, _median, _mode, _stdev, _variance = basic_stats(x, "1d", 0)
|
||||
return x, y_norm
|
||||
|
||||
for i in range (0, len(x), 1):
|
||||
x_norm.append(z_score(x[i], _mean, _stdev))
|
||||
if mode == 'both':
|
||||
_mean, _median, _mode, _stdev, _variance = basic_stats(x, "1d", 0)
|
||||
|
||||
_mean, _median, _mode, _stdev, _variance = basic_stats(y, "1d", 0)
|
||||
for i in range(0, len(x), 1):
|
||||
x_norm.append(z_score(x[i], _mean, _stdev))
|
||||
|
||||
for i in range (0, len(y), 1):
|
||||
y_norm.append(z_score(y[i], _mean, _stdev))
|
||||
_mean, _median, _mode, _stdev, _variance = basic_stats(y, "1d", 0)
|
||||
|
||||
return x_norm, y_norm
|
||||
for i in range(0, len(y), 1):
|
||||
y_norm.append(z_score(y[i], _mean, _stdev))
|
||||
|
||||
else:
|
||||
return x_norm, y_norm
|
||||
|
||||
return error('method error')
|
||||
else:
|
||||
|
||||
def stdev_z_split(mean, stdev, delta, low_bound, high_bound): #returns n-th percentile of spread given mean, standard deviation, lower z-score, and upper z-score
|
||||
return error('method error')
|
||||
|
||||
|
||||
# returns n-th percentile of spread given mean, standard deviation, lower z-score, and upper z-score
|
||||
def stdev_z_split(mean, stdev, delta, low_bound, high_bound):
|
||||
|
||||
z_split = []
|
||||
i = low_bound
|
||||
|
||||
while True:
|
||||
z_split.append(float((1 / (stdev * math.sqrt(2 * math.pi))) * math.e ** (-0.5 * (((i - mean) / stdev) ** 2))))
|
||||
z_split.append(float((1 / (stdev * math.sqrt(2 * math.pi))) *
|
||||
math.e ** (-0.5 * (((i - mean) / stdev) ** 2))))
|
||||
i = i + delta
|
||||
if i > high_bound:
|
||||
break
|
||||
|
||||
return z_split
|
||||
|
||||
|
||||
def histo_analysis(hist_data, delta, low_bound, high_bound):
|
||||
|
||||
if hist_data == 'debug':
|
||||
@ -565,12 +581,12 @@ def histo_analysis(hist_data, delta, low_bound, high_bound):
|
||||
|
||||
for i in range(0, len(hist_data), 1):
|
||||
try:
|
||||
derivative.append(float(hist_data[i - 1]) - float(hist_data [i]))
|
||||
derivative.append(float(hist_data[i - 1]) - float(hist_data[i]))
|
||||
except:
|
||||
pass
|
||||
|
||||
derivative_sorted = sorted(derivative, key=int)
|
||||
mean_derivative = basic_stats(derivative_sorted,"1d", 0)[0]
|
||||
mean_derivative = basic_stats(derivative_sorted, "1d", 0)[0]
|
||||
stdev_derivative = basic_stats(derivative_sorted, "1d", 0)[3]
|
||||
|
||||
predictions = []
|
||||
@ -593,23 +609,26 @@ def histo_analysis(hist_data, delta, low_bound, high_bound):
|
||||
|
||||
return predictions
|
||||
|
||||
|
||||
def poly_regression(x, y, power):
|
||||
|
||||
if x == "null": #if x is 'null', then x will be filled with integer points between 1 and the size of y
|
||||
if x == "null": # if x is 'null', then x will be filled with integer points between 1 and the size of y
|
||||
x = []
|
||||
|
||||
for i in range(len(y)):
|
||||
print(i)
|
||||
x.append(i+1)
|
||||
x.append(i + 1)
|
||||
|
||||
reg_eq = scipy.polyfit(x, y, deg = power)
|
||||
reg_eq = scipy.polyfit(x, y, deg=power)
|
||||
eq_str = ""
|
||||
|
||||
for i in range(0, len(reg_eq), 1):
|
||||
if i < len(reg_eq)- 1:
|
||||
eq_str = eq_str + str(reg_eq[i]) + "*(z**" + str(len(reg_eq) - i - 1) + ")+"
|
||||
if i < len(reg_eq) - 1:
|
||||
eq_str = eq_str + str(reg_eq[i]) + \
|
||||
"*(z**" + str(len(reg_eq) - i - 1) + ")+"
|
||||
else:
|
||||
eq_str = eq_str + str(reg_eq[i]) + "*(z**" + str(len(reg_eq) - i - 1) + ")"
|
||||
eq_str = eq_str + str(reg_eq[i]) + \
|
||||
"*(z**" + str(len(reg_eq) - i - 1) + ")"
|
||||
|
||||
vals = []
|
||||
|
||||
@ -617,108 +636,121 @@ def poly_regression(x, y, power):
|
||||
z = x[i]
|
||||
|
||||
try:
|
||||
exec("vals.append(" + eq_str + ")")
|
||||
exec("vals.append(" + eq_str + ")")
|
||||
except:
|
||||
pass
|
||||
pass
|
||||
|
||||
_rms = rms(vals, y)
|
||||
r2_d2 = r_squared(vals, y)
|
||||
|
||||
return [eq_str, _rms, r2_d2]
|
||||
|
||||
|
||||
def log_regression(x, y, base):
|
||||
|
||||
x_fit = []
|
||||
x_fit = []
|
||||
|
||||
for i in range(len(x)):
|
||||
try:
|
||||
x_fit.append(np.log(x[i]) / np.log(base)) #change of base for logs
|
||||
except:
|
||||
pass
|
||||
for i in range(len(x)):
|
||||
try:
|
||||
# change of base for logs
|
||||
x_fit.append(np.log(x[i]) / np.log(base))
|
||||
except:
|
||||
pass
|
||||
|
||||
reg_eq = np.polyfit(x_fit, y, 1) # y = reg_eq[0] * log(x, base) + reg_eq[1]
|
||||
q_str = str(reg_eq[0]) + "* (np.log(z) / np.log(" + str(base) +"))+" + str(reg_eq[1])
|
||||
vals = []
|
||||
# y = reg_eq[0] * log(x, base) + reg_eq[1]
|
||||
reg_eq = np.polyfit(x_fit, y, 1)
|
||||
q_str = str(reg_eq[0]) + "* (np.log(z) / np.log(" + \
|
||||
str(base) + "))+" + str(reg_eq[1])
|
||||
vals = []
|
||||
|
||||
for i in range(len(x)):
|
||||
z = x[i]
|
||||
for i in range(len(x)):
|
||||
z = x[i]
|
||||
|
||||
try:
|
||||
exec("vals.append(" + eq_str + ")")
|
||||
except:
|
||||
pass
|
||||
try:
|
||||
exec("vals.append(" + eq_str + ")")
|
||||
except:
|
||||
pass
|
||||
|
||||
_rms = rms(vals, y)
|
||||
r2_d2 = r_squared(vals, y)
|
||||
_rms = rms(vals, y)
|
||||
r2_d2 = r_squared(vals, y)
|
||||
|
||||
return eq_str, _rms, r2_d2
|
||||
|
||||
return eq_str, _rms, r2_d2
|
||||
|
||||
def exp_regression(x, y, base):
|
||||
|
||||
y_fit = []
|
||||
y_fit = []
|
||||
|
||||
for i in range(len(y)):
|
||||
try:
|
||||
y_fit.append(np.log(y[i]) / np.log(base)) #change of base for logs
|
||||
except:
|
||||
pass
|
||||
for i in range(len(y)):
|
||||
try:
|
||||
# change of base for logs
|
||||
y_fit.append(np.log(y[i]) / np.log(base))
|
||||
except:
|
||||
pass
|
||||
|
||||
reg_eq = np.polyfit(x, y_fit, 1, w=np.sqrt(y_fit)) # y = base ^ (reg_eq[0] * x) * base ^ (reg_eq[1])
|
||||
eq_str = "(" + str(base) + "**(" + str(reg_eq[0]) + "*z))*(" + str(base) + "**(" + str(reg_eq[1]) + "))"
|
||||
vals = []
|
||||
# y = base ^ (reg_eq[0] * x) * base ^ (reg_eq[1])
|
||||
reg_eq = np.polyfit(x, y_fit, 1, w=np.sqrt(y_fit))
|
||||
eq_str = "(" + str(base) + "**(" + \
|
||||
str(reg_eq[0]) + "*z))*(" + str(base) + "**(" + str(reg_eq[1]) + "))"
|
||||
vals = []
|
||||
|
||||
for i in range(len(x)):
|
||||
z = x[i]
|
||||
for i in range(len(x)):
|
||||
z = x[i]
|
||||
|
||||
try:
|
||||
exec("vals.append(" + eq_str + ")")
|
||||
except:
|
||||
pass
|
||||
try:
|
||||
exec("vals.append(" + eq_str + ")")
|
||||
except:
|
||||
pass
|
||||
|
||||
_rms = rms(vals, y)
|
||||
r2_d2 = r_squared(vals, y)
|
||||
_rms = rms(vals, y)
|
||||
r2_d2 = r_squared(vals, y)
|
||||
|
||||
return eq_str, _rms, r2_d2
|
||||
|
||||
return eq_str, _rms, r2_d2
|
||||
|
||||
def tanh_regression(x, y):
|
||||
|
||||
def tanh (x, a, b, c, d):
|
||||
def tanh(x, a, b, c, d):
|
||||
|
||||
return a * np.tanh(b * (x - c)) + d
|
||||
return a * np.tanh(b * (x - c)) + d
|
||||
|
||||
reg_eq = np.float64(curve_fit(tanh, np.array(x), np.array(y))[0]).tolist()
|
||||
eq_str = str(reg_eq[0]) + " * np.tanh(" + str(reg_eq[1]) + "*(z - " + str(reg_eq[2]) + ")) + " + str(reg_eq[3])
|
||||
vals = []
|
||||
reg_eq = np.float64(curve_fit(tanh, np.array(x), np.array(y))[0]).tolist()
|
||||
eq_str = str(reg_eq[0]) + " * np.tanh(" + str(reg_eq[1]) + \
|
||||
"*(z - " + str(reg_eq[2]) + ")) + " + str(reg_eq[3])
|
||||
vals = []
|
||||
|
||||
for i in range(len(x)):
|
||||
z = x[i]
|
||||
try:
|
||||
exec("vals.append(" + eq_str + ")")
|
||||
except:
|
||||
pass
|
||||
for i in range(len(x)):
|
||||
z = x[i]
|
||||
try:
|
||||
exec("vals.append(" + eq_str + ")")
|
||||
except:
|
||||
pass
|
||||
|
||||
_rms = rms(vals, y)
|
||||
r2_d2 = r_squared(vals, y)
|
||||
_rms = rms(vals, y)
|
||||
r2_d2 = r_squared(vals, y)
|
||||
|
||||
return eq_str, _rms, r2_d2
|
||||
return eq_str, _rms, r2_d2
|
||||
|
||||
def r_squared(predictions, targets): # assumes equal size inputs
|
||||
|
||||
def r_squared(predictions, targets): # assumes equal size inputs
|
||||
|
||||
return metrics.r2_score(np.array(targets), np.array(predictions))
|
||||
|
||||
def rms(predictions, targets): # assumes equal size inputs
|
||||
|
||||
def rms(predictions, targets): # assumes equal size inputs
|
||||
|
||||
_sum = 0
|
||||
|
||||
for i in range(0, len(targets), 1):
|
||||
_sum = (targets[i] - predictions[i]) ** 2
|
||||
|
||||
return float(math.sqrt(_sum/len(targets)))
|
||||
return float(math.sqrt(_sum / len(targets)))
|
||||
|
||||
|
||||
def calc_overfit(equation, rms_train, r2_train, x_test, y_test):
|
||||
|
||||
#performance overfit = performance(train) - performance(test) where performance is r^2
|
||||
#error overfit = error(train) - error(test) where error is rms; biased towards smaller values
|
||||
# performance overfit = performance(train) - performance(test) where performance is r^2
|
||||
# error overfit = error(train) - error(test) where error is rms; biased towards smaller values
|
||||
|
||||
vals = []
|
||||
|
||||
@ -733,19 +765,22 @@ def calc_overfit(equation, rms_train, r2_train, x_test, y_test):
|
||||
|
||||
return r2_train - r2_test
|
||||
|
||||
|
||||
def strip_data(data, mode):
|
||||
|
||||
if mode == "adam": #x is the row number, y are the data
|
||||
if mode == "adam": # x is the row number, y are the data
|
||||
pass
|
||||
|
||||
if mode == "eve": #x are the data, y is the column number
|
||||
if mode == "eve": # x are the data, y is the column number
|
||||
pass
|
||||
|
||||
else:
|
||||
raise error("mode error")
|
||||
|
||||
def optimize_regression(x, y, _range, resolution):#_range in poly regression is the range of powers tried, and in log/exp it is the inverse of the stepsize taken from -1000 to 1000
|
||||
#usage not: for demonstration purpose only, performance is shit
|
||||
|
||||
# _range in poly regression is the range of powers tried, and in log/exp it is the inverse of the stepsize taken from -1000 to 1000
|
||||
def optimize_regression(x, y, _range, resolution):
|
||||
# usage not: for demonstration purpose only, performance is shit
|
||||
if type(resolution) != int:
|
||||
raise error("resolution must be int")
|
||||
|
||||
@ -758,7 +793,7 @@ def optimize_regression(x, y, _range, resolution):#_range in poly regression is
|
||||
x_test = []
|
||||
y_test = []
|
||||
|
||||
for i in range (0, math.floor(len(x) * 0.5), 1):
|
||||
for i in range(0, math.floor(len(x) * 0.5), 1):
|
||||
index = random.randint(0, len(x) - 1)
|
||||
|
||||
x_test.append(x[index])
|
||||
@ -774,7 +809,7 @@ def optimize_regression(x, y, _range, resolution):#_range in poly regression is
|
||||
rmss = []
|
||||
r2s = []
|
||||
|
||||
for i in range (0, _range + 1, 1):
|
||||
for i in range(0, _range + 1, 1):
|
||||
try:
|
||||
x, y, z = poly_regression(x_train, y_train, i)
|
||||
eqs.append(x)
|
||||
@ -783,21 +818,21 @@ def optimize_regression(x, y, _range, resolution):#_range in poly regression is
|
||||
except:
|
||||
pass
|
||||
|
||||
for i in range (1, 100 * resolution + 1):
|
||||
for i in range(1, 100 * resolution + 1):
|
||||
try:
|
||||
x, y, z = exp_regression(x_train, y_train, float(i / resolution))
|
||||
eqs.append(x)
|
||||
rmss.append(y)
|
||||
r2s.append(z)
|
||||
x, y, z = exp_regression(x_train, y_train, float(i / resolution))
|
||||
eqs.append(x)
|
||||
rmss.append(y)
|
||||
r2s.append(z)
|
||||
except:
|
||||
pass
|
||||
|
||||
for i in range (1, 100 * resolution + 1):
|
||||
for i in range(1, 100 * resolution + 1):
|
||||
try:
|
||||
x, y, z = log_regression(x_train, y_train, float(i / resolution))
|
||||
eqs.append(x)
|
||||
rmss.append(y)
|
||||
r2s.append(z)
|
||||
x, y, z = log_regression(x_train, y_train, float(i / resolution))
|
||||
eqs.append(x)
|
||||
rmss.append(y)
|
||||
r2s.append(z)
|
||||
except:
|
||||
pass
|
||||
|
||||
@ -810,13 +845,14 @@ def optimize_regression(x, y, _range, resolution):#_range in poly regression is
|
||||
except:
|
||||
pass
|
||||
|
||||
for i in range (0, len(eqs), 1): #marks all equations where r2 = 1 as they 95% of the time overfit the data
|
||||
# marks all equations where r2 = 1 as they 95% of the time overfit the data
|
||||
for i in range(0, len(eqs), 1):
|
||||
if r2s[i] == 1:
|
||||
eqs[i] = ""
|
||||
rmss[i] = ""
|
||||
r2s[i] = ""
|
||||
|
||||
while True: #removes all equations marked for removal
|
||||
while True: # removes all equations marked for removal
|
||||
try:
|
||||
eqs.remove('')
|
||||
rmss.remove('')
|
||||
@ -826,12 +862,13 @@ def optimize_regression(x, y, _range, resolution):#_range in poly regression is
|
||||
|
||||
overfit = []
|
||||
|
||||
for i in range (0, len(eqs), 1):
|
||||
for i in range(0, len(eqs), 1):
|
||||
|
||||
overfit.append(calc_overfit(eqs[i], rmss[i], r2s[i], x_test, y_test))
|
||||
|
||||
return eqs, rmss, r2s, overfit
|
||||
|
||||
|
||||
def select_best_regression(eqs, rmss, r2s, overfit, selector):
|
||||
|
||||
b_eq = ""
|
||||
@ -860,32 +897,35 @@ def select_best_regression(eqs, rmss, r2s, overfit, selector):
|
||||
|
||||
return b_eq, b_rms, b_r2, b_overfit
|
||||
|
||||
def p_value(x, y): #takes 2 1d arrays
|
||||
|
||||
return stats.ttest_ind(x, y)[1]
|
||||
def p_value(x, y): # takes 2 1d arrays
|
||||
|
||||
def basic_analysis(data): #assumes that rows are the independent variable and columns are the dependant. also assumes that time flows from lowest column to highest column.
|
||||
return stats.ttest_ind(x, y)[1]
|
||||
|
||||
row = len(data)
|
||||
column = []
|
||||
|
||||
for i in range(0, row, 1):
|
||||
column.append(len(data[i]))
|
||||
# assumes that rows are the independent variable and columns are the dependant. also assumes that time flows from lowest column to highest column.
|
||||
def basic_analysis(data):
|
||||
|
||||
column_max = max(column)
|
||||
row_b_stats = []
|
||||
row_histo = []
|
||||
row = len(data)
|
||||
column = []
|
||||
|
||||
for i in range(0, row, 1):
|
||||
row_b_stats.append(basic_stats(data, "row", i))
|
||||
row_histo.append(histo_analysis(data[i], 0.67449, -0.67449, 0.67449))
|
||||
for i in range(0, row, 1):
|
||||
column.append(len(data[i]))
|
||||
|
||||
column_b_stats = []
|
||||
column_max = max(column)
|
||||
row_b_stats = []
|
||||
row_histo = []
|
||||
|
||||
for i in range(0, column_max, 1):
|
||||
column_b_stats.append(basic_stats(data, "column", i))
|
||||
for i in range(0, row, 1):
|
||||
row_b_stats.append(basic_stats(data, "row", i))
|
||||
row_histo.append(histo_analysis(data[i], 0.67449, -0.67449, 0.67449))
|
||||
|
||||
return[row_b_stats, column_b_stats, row_histo]
|
||||
column_b_stats = []
|
||||
|
||||
for i in range(0, column_max, 1):
|
||||
column_b_stats.append(basic_stats(data, "column", i))
|
||||
|
||||
return[row_b_stats, column_b_stats, row_histo]
|
||||
|
||||
|
||||
def benchmark(x, y):
|
||||
@ -900,22 +940,25 @@ def benchmark(x, y):
|
||||
|
||||
return [(end_g - start_g), (end_a - start_a)]
|
||||
|
||||
|
||||
def generate_data(filename, x, y, low, high):
|
||||
|
||||
file = open(filename, "w")
|
||||
|
||||
for i in range (0, y, 1):
|
||||
for i in range(0, y, 1):
|
||||
temp = ""
|
||||
|
||||
for j in range (0, x - 1, 1):
|
||||
temp = str(random.uniform(low, high)) + "," + temp
|
||||
for j in range(0, x - 1, 1):
|
||||
temp = str(random.uniform(low, high)) + "," + temp
|
||||
|
||||
temp = temp + str(random.uniform(low, high))
|
||||
file.write(temp + "\n")
|
||||
|
||||
|
||||
class StatisticsError(ValueError):
|
||||
pass
|
||||
|
||||
|
||||
def _sum(data, start=0):
|
||||
count = 0
|
||||
n, d = _exact_ratio(start)
|
||||
@ -924,7 +967,7 @@ def _sum(data, start=0):
|
||||
T = _coerce(int, type(start))
|
||||
for typ, values in groupby(data, type):
|
||||
T = _coerce(T, typ) # or raise TypeError
|
||||
for n,d in map(_exact_ratio, values):
|
||||
for n, d in map(_exact_ratio, values):
|
||||
count += 1
|
||||
partials[d] = partials_get(d, 0) + n
|
||||
if None in partials:
|
||||
@ -936,26 +979,35 @@ def _sum(data, start=0):
|
||||
total = sum(Fraction(n, d) for d, n in sorted(partials.items()))
|
||||
return (T, total, count)
|
||||
|
||||
|
||||
def _isfinite(x):
|
||||
try:
|
||||
return x.is_finite() # Likely a Decimal.
|
||||
except AttributeError:
|
||||
return math.isfinite(x) # Coerces to float first.
|
||||
|
||||
|
||||
def _coerce(T, S):
|
||||
|
||||
assert T is not bool, "initial type T is bool"
|
||||
|
||||
if T is S: return T
|
||||
if T is S:
|
||||
return T
|
||||
|
||||
if S is int or S is bool: return T
|
||||
if T is int: return S
|
||||
if S is int or S is bool:
|
||||
return T
|
||||
if T is int:
|
||||
return S
|
||||
|
||||
if issubclass(S, T): return S
|
||||
if issubclass(T, S): return T
|
||||
if issubclass(S, T):
|
||||
return S
|
||||
if issubclass(T, S):
|
||||
return T
|
||||
|
||||
if issubclass(T, int): return S
|
||||
if issubclass(S, int): return T
|
||||
if issubclass(T, int):
|
||||
return S
|
||||
if issubclass(S, int):
|
||||
return T
|
||||
|
||||
if issubclass(T, Fraction) and issubclass(S, float):
|
||||
return S
|
||||
@ -965,6 +1017,7 @@ def _coerce(T, S):
|
||||
msg = "don't know how to coerce %s and %s"
|
||||
raise TypeError(msg % (T.__name__, S.__name__))
|
||||
|
||||
|
||||
def _exact_ratio(x):
|
||||
|
||||
try:
|
||||
@ -988,6 +1041,7 @@ def _exact_ratio(x):
|
||||
msg = "can't convert type '{}' to numerator/denominator"
|
||||
raise TypeError(msg.format(type(x).__name__))
|
||||
|
||||
|
||||
def _convert(value, T):
|
||||
|
||||
if type(value) is T:
|
||||
@ -1000,10 +1054,11 @@ def _convert(value, T):
|
||||
return T(value)
|
||||
except TypeError:
|
||||
if issubclass(T, Decimal):
|
||||
return T(value.numerator)/T(value.denominator)
|
||||
return T(value.numerator) / T(value.denominator)
|
||||
else:
|
||||
raise
|
||||
|
||||
|
||||
def _counts(data):
|
||||
|
||||
table = collections.Counter(iter(data)).most_common()
|
||||
@ -1029,8 +1084,8 @@ def _find_lteq(a, x):
|
||||
def _find_rteq(a, l, x):
|
||||
|
||||
i = bisect_right(a, x, lo=l)
|
||||
if i != (len(a)+1) and a[i-1] == x:
|
||||
return i-1
|
||||
if i != (len(a) + 1) and a[i - 1] == x:
|
||||
return i - 1
|
||||
raise ValueError
|
||||
|
||||
|
||||
@ -1041,6 +1096,7 @@ def _fail_neg(values, errmsg='negative value'):
|
||||
raise StatisticsError(errmsg)
|
||||
yield x
|
||||
|
||||
|
||||
def mean(data):
|
||||
|
||||
if iter(data) is data:
|
||||
@ -1050,7 +1106,8 @@ def mean(data):
|
||||
raise StatisticsError('mean requires at least one data point')
|
||||
T, total, count = _sum(data)
|
||||
assert count == n
|
||||
return _convert(total/n, T)
|
||||
return _convert(total / n, T)
|
||||
|
||||
|
||||
def median(data):
|
||||
|
||||
@ -1058,11 +1115,12 @@ def median(data):
|
||||
n = len(data)
|
||||
if n == 0:
|
||||
raise StatisticsError("no median for empty data")
|
||||
if n%2 == 1:
|
||||
return data[n//2]
|
||||
if n % 2 == 1:
|
||||
return data[n // 2]
|
||||
else:
|
||||
i = n//2
|
||||
return (data[i - 1] + data[i])/2
|
||||
i = n // 2
|
||||
return (data[i - 1] + data[i]) / 2
|
||||
|
||||
|
||||
def mode(data):
|
||||
|
||||
@ -1071,23 +1129,25 @@ def mode(data):
|
||||
return table[0][0]
|
||||
elif table:
|
||||
raise StatisticsError(
|
||||
'no unique mode; found %d equally common values' % len(table)
|
||||
)
|
||||
'no unique mode; found %d equally common values' % len(table)
|
||||
)
|
||||
else:
|
||||
raise StatisticsError('no mode for empty data')
|
||||
|
||||
|
||||
def _ss(data, c=None):
|
||||
|
||||
if c is None:
|
||||
c = mean(data)
|
||||
T, total, count = _sum((x-c)**2 for x in data)
|
||||
T, total, count = _sum((x - c)**2 for x in data)
|
||||
|
||||
U, total2, count2 = _sum((x-c) for x in data)
|
||||
U, total2, count2 = _sum((x - c) for x in data)
|
||||
assert T == U and count == count2
|
||||
total -= total2**2/len(data)
|
||||
total -= total2**2 / len(data)
|
||||
assert not total < 0, 'negative sum of square deviations: %f' % total
|
||||
return (T, total)
|
||||
|
||||
|
||||
def variance(data, xbar=None):
|
||||
|
||||
if iter(data) is data:
|
||||
@ -1096,7 +1156,8 @@ def variance(data, xbar=None):
|
||||
if n < 2:
|
||||
raise StatisticsError('variance requires at least two data points')
|
||||
T, ss = _ss(data, xbar)
|
||||
return _convert(ss/(n-1), T)
|
||||
return _convert(ss / (n - 1), T)
|
||||
|
||||
|
||||
def stdev(data, xbar=None):
|
||||
|
||||
|
||||
Binary file not shown.
Binary file not shown.
BIN
data analysis/build/temp.win-amd64-3.7/Release/analysis.obj
Normal file
BIN
data analysis/build/temp.win-amd64-3.7/Release/analysis.obj
Normal file
Binary file not shown.
Binary file not shown.
Binary file not shown.
BIN
data analysis/build/temp.win-amd64-3.7/Release/c_analysis.obj
Normal file
BIN
data analysis/build/temp.win-amd64-3.7/Release/c_analysis.obj
Normal file
Binary file not shown.
5
data analysis/setup.py
Normal file
5
data analysis/setup.py
Normal file
@ -0,0 +1,5 @@
|
||||
from distutils.core import setup
|
||||
from Cython.Build import cythonize
|
||||
|
||||
setup(name='analysis',
|
||||
ext_modules=cythonize("analysis.py"))
|
||||
Loading…
Reference in New Issue
Block a user