search_algos.py

search_algos.py

@@ -1,106 +1,82 @@
 from complexity import time_and_space_profiler
-from tqdm import tqdm , trange
+from tqdm import tqdm
 import numpy as np
 import pandas as pd
 
-
-
-# Inialization logic
-# TODO: 30 tests should be implemented for 
-#       1000;10000;100000;1000000;10000000
-
+# Initialization logic
+# Generating 30 tests for arrays of lengths between 1000 and 10,000,000 with 5 tests per length
 np.random.seed(42)
 
 tests = []
-
-#lenghts = [1000,10000,100000,1000000]
-
-lenghts = np.array(range(1000,1000000,20000))
-
+lengths = np.array(range(1000, 10_000_000, 200_000))
 tests_per_length = 5
 
-for length in lenghts:
+for length in lengths:
     for _ in range(tests_per_length):
-
-        val = np.sort(np.random.randint(1,4*length,size=length))
-
-        target = np.random.randint(1,4*length)
-
-        test = (length, val, target)
-
-        tests.append(test)
-
+        # Generate a sorted array and a random target
+        val = np.sort(np.random.randint(1, 4 * length, size=length))
+        target = np.random.randint(1, 4 * length)
+        tests.append((length, val, target))
 
 # Function definitions
 
 @time_and_space_profiler
-def sequantial_search(val,target):
+def sequential_search(val, target):
+    """Performs a simple sequential search."""
     for i in range(len(val)):
-        if target == val[i]: # comparision
-            return i+1
-
+        if target == val[i]:  # Comparison
+            return i + 1
     return len(val)
 
-#@time_and_space_profiler
-#def quadratic_sequantial_search(val,target):
-#    for i in range(len(val)):
-#        for j in range(len(val)):
-#            if target == val[i]: # comparision
-#                return i+1
-#    
-#    return len(val)*len(val)
-
 @time_and_space_profiler
-def advanced_sequantial_search(val,target):
+def advanced_sequential_search(val, target):
+    """Optimized sequential search that stops early when the target is less than the current element."""
     comparison = 0
     for i in range(len(val)):
-        comparison+=2
-        if target == val[i]: # comparision
-            comparison-=1
+        comparison += 2
+        if target == val[i]:  # Match found
+            comparison -= 1
             break
-        # add the part to stop searching when target small to the element
-        elif target < val[i]:
+        elif target < val[i]:  # No need to search further
             break
-
     return comparison
 
 @time_and_space_profiler
-def binary_search(val,target):
-	
+def binary_search(val, target):
+    """Performs binary search."""
     start = 0
-    end = len(val)-1
+    end = len(val) - 1
     comparison = 1
 
-    while start < end:
-        half = (end + start)//2
-        comparison+=2
-        if target == val[half]:
-            comparison-=1
+    while start <= end:
+        half = (end + start) // 2
+        comparison += 2
+        if target == val[half]:  # Match found
+            comparison -= 1
             break
-        elif target < val[half]:
-            end = half -1
-        else:
-            start = half + 1 
-        comparison+=1
-    return comparison 
-
-funcs = [sequantial_search, advanced_sequantial_search,binary_search]
+        elif target < val[half]:  # Search left
+            end = half - 1
+        else:  # Search right
+            start = half + 1
+        comparison += 1
+    return comparison
 
+# List of functions to test
+funcs = [sequential_search, advanced_sequential_search, binary_search]
+
+# Run tests and collect results
 results = []
-for i , (length, val ,target) in tqdm(enumerate(tests),ncols=len(tests)):
-
+for i, (length, val, target) in tqdm(enumerate(tests), total=len(tests), desc="Testing progress"):
     for func in funcs:
+        func_name, comparison, T, S = func(val, target)
+        results.append((i, func_name, length, comparison, T, S))
 
-        func_name,comparison,T, S = func(val,target)
-
-        results.append((i,func_name,length,comparison,T,S))
-
-
-# Printing results
-#print(results)
-
-df = pd.DataFrame(results, columns=['id_test','function_name','array_length','comparison','time','space'])
+# Convert results to a DataFrame
+df = pd.DataFrame(results, columns=['id_test', 'function_name', 'array_length', 'comparison', 'time', 'space'])
 
+# Output results
 print(df)
 
-df.to_csv('results.csv', index=False)
+# Save results to a CSV file
+df.to_csv('results.csv', index=False)
+