55 lines
2.0 KiB
Python
Executable File
55 lines
2.0 KiB
Python
Executable File
import numpy as np
|
|
import scipy.stats as s
|
|
import glob as glob # glob
|
|
import pandas as pd
|
|
|
|
filelist = glob.glob("hw3_*.txt")
|
|
filelist.sort()
|
|
|
|
def read(file):
|
|
fileobj = open(file, "r")
|
|
outputstr = fileobj.readlines()
|
|
fileobj.close()
|
|
outputarray = np.zeros(len(outputstr))
|
|
for i in np.arange(len(outputstr)):
|
|
outputarray[i] = float(outputstr[i])
|
|
return outputarray
|
|
|
|
parameters = ["mean", "median", "std", "iqr", "skew", "kurtosis"]
|
|
|
|
for i in range(len(filelist)):
|
|
print(filelist[i])
|
|
data = np.array(read(filelist[i]))
|
|
for n in range (len(parameters)):
|
|
operation = parameters[n]
|
|
print(str(operation) + " " + np.operation(data))
|
|
|
|
|
|
#for n in range(len(filelist)):
|
|
# print(filelist[n])
|
|
# mean = np.mean(read(filelist[n]))
|
|
# print("mean: " + str(mean))
|
|
# median = np.median(read(filelist[n]))
|
|
# print("median: " + str(median))
|
|
# stddev = np.std(read(filelist[n]))
|
|
# print("stddev: " + str(stddev))
|
|
# iqr = s.iqr(read(filelist[n]))
|
|
# print("iqr: " + str(iqr))
|
|
# skew = s.skew(read(filelist[n]))
|
|
# print("skew: " + str(skew))
|
|
# kurtosis = s.kurtosis(read(filelist[n]))
|
|
# print("kurtosis: " + str(kurtosis)+"\n")
|
|
|
|
# the mean and median are similar for all files, indicating solid, outlier free data.
|
|
# standard deviation is quite high for everything except wind shear, indicating either \
|
|
# inconsistent readings for everything but wind shear, or more likely, smaller units and \
|
|
# higher rates of change.
|
|
# the difference between shr1's iqr and stddev is larger than that of shr2's (shr2's is \
|
|
# quite close to its stddev), possibility of one minor outlier
|
|
# none of the data is very skewed, the largest (absolute value) being 0.54896, and \
|
|
# all of the data has negative kurtosis, meaning when distibuted, it will have a shallower \
|
|
# peak than the bell curve (e^x^2)
|
|
# the february and may datasets are similar in that their wind shears are similar, though \
|
|
# mays is still larger. they are different in that mays SRH and CAPE are both much higher, \
|
|
# so mays tornadoes are much stronger.
|