From 5a0e37580a7beb79a66223884653ffabaca118f4 Mon Sep 17 00:00:00 2001
From: Safak <safak.hazinedar@startmail.com>
Date: Wed, 23 Apr 2025 15:47:17 +0200
Subject: [PATCH] Reduzierung auf eine Dict in der die Eigenschaften count,
 p(x_i) und I(x_i) geschrieben werden

---
 P1/main.py | 82 +++++++++++++++++++++---------------------------------
 1 file changed, 31 insertions(+), 51 deletions(-)

diff --git a/P1/main.py b/P1/main.py
index 17b92f7..5ceeff5 100644
--- a/P1/main.py
+++ b/P1/main.py
@@ -1,6 +1,11 @@
 import math
 from operator import concat
 
+empty_element = {
+    "count" : 1,
+    "p(x_i)" : 0,
+    "I(x_i)" : 0
+}
 
 def read_text_file():
     path = '/Users/safak/Documents/UNI/IT/P1/text.txt'
@@ -9,58 +14,47 @@ def read_text_file():
         content = file.read()
     return content
 
-
 def Z_statistik():
     # Ergebnisse mit https://de.planetcalc.com/2476/ prüfbar
     message = read_text_file()
 
-    # Anzahl der Zeichen in der Nachricht X
     m = len(message)
 
-    # Häufigkeiten der Zeichen in der Nachricht X
-    char_count = {} #Dictionary
+    elements = {}
 
     for char in message:
-        if char_count.__contains__(char):
-            char_count[char] += 1
+        if elements.__contains__(char):
+            elements[char]["count"] += 1
         else:
-            char_count[char] = 1
-
-    calculate(char_count, m, message)
+            elements[char] = empty_element.copy()
 
+    calculate(elements, m, message)
 
 def Z2_statistik():
     message = read_text_file()
 
-    # Anzahl der Tupel in der Nachricht
     m = len(message) - 1        # Letztes Zeichen kann kein Tupel mit "nichts" bilden
 
-    # welche Zeichen kommen wie oft vor?
-    char_count = {} #Dictionary
+    elements = {}
 
     for i, char in enumerate(message):
         if i != m:
             tuple = char + message[i+1]
-            if char_count.__contains__(tuple):
-                char_count[tuple] += 1
+            if elements.__contains__(tuple):
+                elements[tuple]["count"] += 1
             else:
-                char_count[tuple] = 1
+                elements[tuple] = empty_element.copy()
 
-
-    calculate(char_count, m, message)
+    calculate(elements, m, message)
 
 def W_statistik():
     message = read_text_file()
 
-    # Anzahl der Wörter in der Nachricht
     m = 0
-
-    # welche Zeichen kommen wie oft vor?
-    word_count = {} #Dictionary
-
-    enumerate(message)
     i = 0
 
+    elements = {}
+
     while i != len(message):
         word = ""
 
@@ -77,48 +71,34 @@ def W_statistik():
             m += 1
 
             # Zähle die Häufigkeit der Wörter
-            if word_count.__contains__(word):
-                word_count[word] += 1
+            if elements.__contains__(word):
+                elements[word]["count"] += 1
             else:
-                word_count[word] = 1
+                elements[word] = empty_element.copy()
 
         # gehe weiter in der Nachricht
         i += 1
 
-    calculate(word_count, m, message)
+    calculate(elements, m, message)
 
+def calculate(elements, m, message):
+    for x_i in elements:
+        elements[x_i]["p(x_i)"] = elements[x_i]["count"] / m
+        elements[x_i]["I(x_i)"] = -1 * math.log2(elements[x_i]["p(x_i)"])
 
-
-def calculate(collection, m, message):
-    # Wahrscheinlichkeit von x_i
-    p_X = {}
-    for x_i in collection:
-        p_X[x_i] = collection[x_i] / m
-
-    # Informationsgehalt I(x_i) = -log_{2}(p(x_i))
-    i_X = {}
-    for x_i in p_X:
-        i_X[x_i] = -1 * math.log2(p_X[x_i])
-
-    # Entropie H(X) = sum_{i=1}{M}(p(x_i)*I(x_i))
-    h_X = 0
-    for x_i in i_X:
-        h_X += p_X[x_i] * i_X[x_i]
+    h = 0
+    for x_i in elements:
+        h += elements[x_i]["p(x_i)"] * elements[x_i]["I(x_i)"]
 
     # Ausgabe
-    print("Nachricht:")
-    print(message)
-
-    for x_i in sorted(i_X):
-        print(f"{x_i:<20}: {collection[x_i]:<5} : {i_X[x_i]:<10}")
-    print("Entropie der Nachricht = " + h_X.__str__())
-
+    for x_i in elements:
+        print(f"{elements[x_i]["count"]:3.0f} | {elements[x_i]["I(x_i)"]:15.12f} | »{x_i}«")
+    print("Entropie der Nachricht = " + h.__str__())
 
 def main():
     Z_statistik()
     Z2_statistik()
     W_statistik()
 
-
 if __name__ == '__main__':
     main()
\ No newline at end of file