updated readme with infocalc info

.gitignore

@@ -1,2 +1,5 @@
 *~
 *.log
+flycheck_*.py
+\#*#
+test.pdf

README.md

@@ -1,3 +1,5 @@
 # ad-calc
 
 Tools to help calculating values for Axiomatic Design analysis
+
+`infocalc.py` calculates information content based upon a csv file or statistical parameters and upper/lower limits

infocalc.py

@@ -11,7 +11,8 @@ from pathlib import PurePath##https://docs.python.org/3/library/pathlib.html#mod
 import numpy as np
 import matplotlib
 import matplotlib.pyplot as plt
-from scipy.stats import norm
+from scipy.stats import norm,t
+import scipy.stats
 import pandas as pd
 
 #Main program loop
@@ -96,25 +97,23 @@ if args.mode == "DATA":
     data = np.array(pd.read_csv(inpath)[args.column])
     mean = data.mean()
     stddev = data.std(ddof=1)
+    # Delta Degrees of Freedom: ddof=0 for population, ddof=1 for sample std dev
     samplesize = len(data)
 elif args.mode == "SIM":
     mean = args.mean
     stddev = args.stddev
     samplesize = args.samplesize
+df = samplesize - 1 
     
-# time to deal with the bounds
-    
-# Delta Degrees of Freedom: ddof=0 for population, ddof=1 for sample std dev
 prob = 0
 if args.upperbound and args.lowerbound:
-    prob = norm.cdf(args.upperbound, mean, stddev) - norm.cdf(args.lowerbound, mean, stddev)
+    prob = t.cdf(df,args.upperbound, mean, stddev) - t.cdf(df,args.lowerbound, mean, stddev)
 elif args.upperbound:
-    prob = norm.cdf(args.upperbound, mean, stddev)
+    prob = t.cdf(df,args.upperbound, mean, stddev)
 elif args.lowerbound:
-    prob = 1 - norm.cdf(args.lowerbound, mean, stddev)
+    prob = 1 - t.cdf(df,args.lowerbound, mean, stddev)
 else:
     prob = 1# no bounds set!
-    ##TODO!!!!
 #print("probability: %f", prob)
 info = -np.emath.log2(prob)
 #print("information content: %f bits", info)

normdist.py

@@ -1,57 +0,0 @@
-#!/usr/bin/env python
-import numpy as np
-import matplotlib.pyplot as plt
-from scipy.stats import norm
-
-## Data goes here for now --foley
-data = np.array([1, 1.1, 0.9, 1, 1, 0.9, 0.9])
-lowerbound = 0.9
-upperbound = 1.0
-
-mean = data.mean()
-stddev = data.std(ddof=1)
-# Delta Degrees of Freedom: ddof=0 for population, ddof=1 for sample std dev
-prob = norm.cdf(upperbound, mean, stddev) - norm.cdf(lowerbound, mean, stddev)
-#print("probability: %f", prob)
-info = -np.emath.log2(prob)
-#print("information content: %f bits", info)
-## place text on plot:  https://matplotlib.org/3.3.4/gallery/recipes/placing_text_boxes.html
-fig, ax = plt.subplots()
-textstr = '\n'.join((
-    r'$n=%d$' % (len(data)),
-    r'$\mu=%.2f$' % (mean, ),
-    r'$\sigma=%.2f$' % (stddev, ),
-    r'$P=%.2f$' % (prob, ),
-    r'$I=%.2f$ bits' % (info, )))
-# these are matplotlib.patch.Patch properties
-props = dict(boxstyle='round', facecolor='wheat', alpha=0.5)
-
-# place a text box in upper left in axes coords
-ax.text(0.05, 0.95, textstr, transform=ax.transAxes, fontsize=14,
-        verticalalignment='top', bbox=props)
-
-x = np.linspace(mean-3*stddev, mean+3*stddev, 500)
-y = norm.pdf(x, loc=mean, scale=stddev) * stddev#rescale back to unity area
-plt.axvline(x=mean, color="green", linestyle="dashed", label="mean")
-plt.axvline(lowerbound, color="red")
-plt.axvline(upperbound, color="red")
-
-plt.plot(x, y, 'b-', label='Normal distribution')
-#yt = scipy.stats.t.pdf(x, len(data)-1, mean, stddev)
-#plt.plot(x, yt, 'g-', label='T Distribution')
-coloredregion = (x >= lowerbound) & ( x <= upperbound ) #select x values
-plt.fill_between(x, 0, y, where=coloredregion, color="grey", alpha=0.5, label="Design range")
-plt.xlabel('X')
-plt.ylabel('Probability density')
-plt.legend()
-plt.grid(True)
-
-top = plt.ylim()[1]
-
-
-plt.show()
-# annotate values on X after drawing the graphs
-
-
-
-

pandas-test.py

@@ -1,23 +0,0 @@
-#!/usr/bin/env python
-import pandas as pd
-
-df = pd.DataFrame(
-    {
-        "Name": [
-            "Braund, Mr. Owen Harris",
-            "Allen, Mr. William Hentry",
-            "Bonnell, Miss. Elizabeth",
-            ],
-        "Age": [22, 35, 58],
-        "Sex": ["male", "male", "female"],
-    }       
-)
-
-print(df.describe())
-
-titanic = pd.read_csv("titanic.csv")
-print(titanic.head(8))
-titanic.to_excel("titanic.xlsx", sheet_name="passengers", index=False)
-titanic_xltest = pd.read_excel("titanic.xlsx", sheet_name="passengers")
-print("INFO")
-print(titanic.info())

tests.sh

@@ -1,6 +1,6 @@
 #!/bin/bash
 # Get infocalc.py from https://gitea.cs.ru.is/AxiomaticDesign/adcalc
 echo "Loading data from file"
-./infocalc.py DATA testdata.csv data1 0.9 1.1 --graphinfo
+./infocalc.py --lowerbound 0.9 --upperbound 1.1 --graphinfo DATA testdata.csv data1
 echo "Creating simulated curve from parameters"
-./infocalc.py SIM 8 1.0 0.5 0.9 1.1
+./infocalc.py --lowerbound 0.9 --upperbound 1.1 SIM 8 1.0 0.5