clip-protocol 2.2.13__tar.gz → 2.3__tar.gz

{clip_protocol-2.2.13 → clip_protocol-2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: clip_protocol
-Version: 2.2.13
+Version: 2.3
 Summary: Protocol to ensure the privatization of 
 Project-URL: Homepage, https://github.com/martaajonees/Local_Privacy
 Project-URL: Issues, https://github.com/martaajonees/Local_Privacy/issues

clip_protocol-2.3/evaluation/AOI datasets/process.py

@@ -0,0 +1,57 @@
+import pandas as pd
+import glob
+import os
+
+# Carpeta actual donde está el script
+current_folder = os.getcwd()
+
+# Buscar todos los archivos .xlsx en la carpeta actual
+xlsx_files = glob.glob(os.path.join(current_folder, "*.xlsx"))
+
+for file_path in xlsx_files:
+    try:
+        # Leer el archivo
+        df_temp = pd.read_excel(file_path)
+
+        if any(col.startswith("Unnamed") for col in df_temp.columns):
+            df = pd.read_excel(file_path, header=1)  
+        else:
+            df = df_temp
+
+        # --- MEJORA: Limpiar nombres de columnas ---
+        # Eliminamos espacios en blanco extra y pasamos a minúsculas para comparar fácilmente
+        df.columns = [str(c).strip() for c in df.columns]
+        cols_lower = [c.lower() for c in df.columns]
+
+        # Buscamos los índices de las columnas que necesitamos (sin importar mayúsculas)
+        target_p = 'participant'
+        target_a = 'aoi hit'
+
+        if target_p in cols_lower and target_a in cols_lower:
+            # Identificar los nombres reales de las columnas en este archivo específico
+            real_col_p = df.columns[cols_lower.index(target_p)]
+            real_col_a = df.columns[cols_lower.index(target_a)]
+
+            # Obtener el nombre del archivo sin extensión para el participante
+            participant_name = os.path.splitext(os.path.basename(file_path))[0]
+
+            # Reemplazar valores y filtrar
+            df[real_col_p] = participant_name
+            
+            # Mantener solo las dos columnas y limpiar nulos
+            df = df[[real_col_p, real_col_a]]
+            df = df[df[real_col_a].notna()]
+
+            # Renombrar a los nombres finales deseados
+            df.columns = ['Participant', 'AOI hit']
+
+            # Sobrescribir el archivo original
+            df.to_excel(file_path, index=False)
+            print(f"✅ Procesado: {os.path.basename(file_path)}")
+        else:
+            print(f"❌ Columnas no encontradas en {os.path.basename(file_path)}. Columnas detectadas: {list(df.columns)}")
+
+    except Exception as e:
+        print(f"⚠️ Error procesando {os.path.basename(file_path)}: {e}")
+
+print("\nProceso finalizado.")

{clip_protocol-2.2.13 → clip_protocol-2.3}/evaluation/experiment_1.py

@@ -24,38 +24,6 @@ def run_command(e, k, m, df, privacy_method):
 
     return compute_error_table(get_real_frequency(df), df_estimated, 2), df_estimated
 
-
-def plot_latex(errors, path):
-    lines = [
-        r"\begin{figure}[h]",
-        r"\centering",
-        r"\begin{tikzpicture}",
-        r"\begin{axis}[",
-        r"  xlabel={$\epsilon$}, ylabel={Error},",
-        r"  legend style={at={(0.5,-0.15)}, anchor=north,legend columns=-1},",
-        r"  xmin=0, grid=major, width=12cm, height=8cm,",
-        r"  cycle list name=color list,",
-        r"]"
-    ]
-
-    for metric, points in errors.items():
-        name = "Lp Norm" if metric == "Lρ Norm" else metric
-        lines.append(r"\addplot coordinates {")
-        lines += [f"  ({eps}, {err})" for eps, err in sorted(points)]
-        lines.append(r"};")
-        lines.append(fr"\addlegendentry{{{name}}}")
-
-    lines += [
-        r"\end{axis}",
-        r"\end{tikzpicture}",
-        r"\caption{Evolución del error por métrica en función del parámetro $\epsilon$}",
-        r"\end{figure}"
-    ]
-
-    with open(path, "w") as f:
-        f.write("\n".join(lines))
-    print(f"✅ LaTeX graph saved to {path}")
-
 def run_experiment1(df, privacy_method):
     k = int(input("🔑 Enter k value: "))
     m = int(input("🔢 Enter m value: "))
@@ -65,13 +33,13 @@ def run_experiment1(df, privacy_method):
     epsilons = [round(e, 1) for e in list(reversed([x * 0.5 for x in range(1, 21)])) + [0.4, 0.3, 0.2, 0.1]]
 
     for eps in epsilons:
-        table, _ = run_command(eps, k, m, df, method)
+        print(f"Running with epsilon: {eps}")
+        table, _ = run_command(eps, k, m, df, privacy_method)
         for metric, val in table:
             error_history.setdefault(metric, []).append((eps, val))
     
     df = pd.DataFrame(error_history)
-    df.to_csv(f"figures/table_experiment_1_{privacy_method}.csv", index=False)
-    plot_latex(error_history, f"figures/experiment_1_{privacy_method}.tex")
+    df.to_csv(f"table_experiment_1_{privacy_method}.csv", index=False)
         
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description="Run experiment 1")
@@ -79,8 +47,8 @@ if __name__ == "__main__":
     args = parser.parse_args()
     
     distribution = input(" Enter the distribution 1/2/3/4: ")
-
-    pattern = f"aoi-hits-d{distribution}-5000"
+    
+    pattern = f"SynLog-5000-d{distribution}"
     matching_files = [f for f in os.listdir(args.f) if pattern in f and f.endswith(".xlsx")]
 
     file_path = os.path.join(args.f, matching_files[0])

{clip_protocol-2.2.13 → clip_protocol-2.3}/evaluation/experiment_2.py

@@ -115,7 +115,7 @@ def run_experiment_2(datasets_by_size, params):
                   "Iteraciones PCMeS", "Tiempo de ejecución PCMeS"]
     df_pivot = df_pivot[final_cols]
 
-    df_pivot.to_csv("figures/table_experiment_2.csv", index=False)
+    df_pivot.to_csv("table_experiment_2.csv", index=False)
 
 
 if __name__ == "__main__":
@@ -133,7 +133,8 @@ if __name__ == "__main__":
 
     datasets = {}
     for size in sizes:
-        pattern = f"aoi-hits-d{distribution}-{size}"
+        
+        pattern = f"SynLog-{size}-d{distribution}"
         file_path = os.path.join(args.f, pattern + ".xlsx")
         header = 1 if "Unnamed" in pd.read_excel(file_path, nrows=1).columns[0] else 0
         df = pd.read_excel(file_path, header=header)

{clip_protocol-2.2.13 → clip_protocol-2.3}/evaluation/experiment_3.py

@@ -66,7 +66,8 @@ def optimize_e(k, m, df, e_r, privacy_level, error_value, tolerance, privacy_met
 def run_experiment_3(datasets, params):
     error_value = 0.05
     tolerance = 0.01
-    privacy_level = "high"
+    # privacy_level = "high"
+    privacy_level = "low"
 
     for method in ["PCMeS", "PHCMS"]:
         row_apple = {"Método": "Método de Apple"}
@@ -89,7 +90,7 @@ def run_experiment_3(datasets, params):
             row_clip[size] = f"{epsilon:.2f} / {pe_error:.2f}"
         
         df_result = pd.DataFrame([row_apple, row_clip])
-        df_result.to_csv(f"figures/table_experiment_3_{method}.csv", index=False)
+        df_result.to_csv(f"table_experiment_3_{method}.csv", index=False)
         
 
 if __name__ == "__main__":
@@ -107,11 +108,11 @@ if __name__ == "__main__":
 
     datasets = {}
     for size in sizes:
-        pattern = f"aoi-hits-d{distribution}-{size}"
+        pattern = f"SynLog-{size}-d{distribution}"
         file_path = os.path.join(args.f, pattern + ".xlsx")
         header = 1 if "Unnamed" in pd.read_excel(file_path, nrows=1).columns[0] else 0
         df = pd.read_excel(file_path, header=header)
         datasets[size] = df
         
     
-    run_experiment_3(datasets, params)
+    run_experiment_3(datasets, params)

{clip_protocol-2.2.13 → clip_protocol-2.3}/evaluation/experiment_4.py

@@ -84,7 +84,7 @@ def run_experiment_4(datasets, params):
             cleaned_table = [[col[0], col[1].replace('%', '') if isinstance(col[1], str) else col[1]] for col in filtered_table]
 
             error_by_aoi = pd.DataFrame(cleaned_table, columns=['AOI', 'Error'])
-            path_individual = f"figures/experimet_4_d{distribution}_{method}.csv"
+            path_individual = f"experimet_4_d{distribution}_{method}.csv"
             error_by_aoi.to_csv(path_individual, index=False)
         
 if __name__ == "__main__":
@@ -101,7 +101,7 @@ if __name__ == "__main__":
 
     datasets = {}
     for distribution in distributions:
-        pattern = f"aoi-hits-d{distribution}-5000"
+        pattern = f"SynLog-5000-d{distribution}"
         file_path = os.path.join(args.f, pattern + ".xlsx")
         header = 1 if "Unnamed" in pd.read_excel(file_path, nrows=1).columns[0] else 0
         df = pd.read_excel(file_path, header=header)

{clip_protocol-2.2.13 → clip_protocol-2.3}/evaluation/experiment_5.py

@@ -149,10 +149,10 @@ def run_experiment_5(datasets, privatized_path):
             privatized_data.to_csv(filename, index=False)
     
     performance_df = pd.DataFrame(performance_records)
-    performance_df.to_csv("figures/experiment_5.csv", index=False)
+    performance_df.to_csv("experiment_5.csv", index=False)
 
     size_df = pd.DataFrame(size_comparison_records)
-    size_df.to_csv("figures/experiment_5_size_comparison.csv", index=False)
+    size_df.to_csv("experiment_5_size_comparison.csv", index=False)
 
 def load_excel_with_header_check(filepath):
     try:

{clip_protocol-2.2.13 → clip_protocol-2.3}/evaluation/figures/experiment_2_params.json

@@ -6,7 +6,7 @@
   },
   "PHCMS": {
     "k": 145,
-    "m": 128,
+    "m": 256,
     "e_r": 8.0
   }
-}
+}

clip_protocol-2.3/evaluation/frecuencias_por_archivo.csv

@@ -0,0 +1,60 @@
+Archivo,Campo,Frecuencia
+s01-event-statistics-single.xlsx,AOI 003,4720
+s01-event-statistics-single.xlsx,AOI 002,191
+s01-event-statistics-single.xlsx,AOI 001,89
+s02-event-statistics-single.xlsx,AOI 003,2518
+s02-event-statistics-single.xlsx,AOI 001,123
+s02-event-statistics-single.xlsx,AOI 002,85
+s03-event-statistics-single.xlsx,AOI 003,3850
+s03-event-statistics-single.xlsx,AOI 002,159
+s03-event-statistics-single.xlsx,AOI 001,6
+s04-event-statistics-single.xlsx,AOI 003,2923
+s04-event-statistics-single.xlsx,AOI 002,636
+s04-event-statistics-single.xlsx,AOI 001,338
+s05-event-statistics-single.xlsx,AOI 003,4465
+s05-event-statistics-single.xlsx,AOI 002,475
+s05-event-statistics-single.xlsx,AOI 001,40
+s06-event-statistics-single.xlsx,AOI 003,3739
+s06-event-statistics-single.xlsx,AOI 002,326
+s06-event-statistics-single.xlsx,AOI 001,103
+s07-event-statistics-single.xlsx,AOI 003,6733
+s07-event-statistics-single.xlsx,AOI 002,645
+s07-event-statistics-single.xlsx,AOI 001,33
+s08-event-statistics-single.xlsx,AOI 003,2619
+s08-event-statistics-single.xlsx,AOI 002,154
+s08-event-statistics-single.xlsx,AOI 001,36
+s09-event-statistics-single.xlsx,AOI 003,5409
+s09-event-statistics-single.xlsx,AOI 002,270
+s09-event-statistics-single.xlsx,AOI 001,222
+s11-event-statistics-single.xlsx,AOI 003,2902
+s11-event-statistics-single.xlsx,AOI 002,129
+s11-event-statistics-single.xlsx,AOI 001,93
+s12-event-statistics-single.xlsx,AOI 003,2158
+s12-event-statistics-single.xlsx,AOI 002,48
+s12-event-statistics-single.xlsx,AOI 001,3
+s13-event-statistics-single.xlsx,AOI 003,3634
+s13-event-statistics-single.xlsx,AOI 002,329
+s13-event-statistics-single.xlsx,AOI 001,68
+s14-event-statistics-single.xlsx,AOI 003,2531
+s14-event-statistics-single.xlsx,AOI 002,85
+s16-event-statistics-single.xlsx,AOI 003,4210
+s16-event-statistics-single.xlsx,AOI 002,218
+s16-event-statistics-single.xlsx,AOI 001,117
+s18-event-statistics-single.xlsx,AOI 003,1367
+s18-event-statistics-single.xlsx,AOI 001,10
+s18-event-statistics-single.xlsx,AOI 002,6
+s19-event-statistics-single.xlsx,AOI 003,2882
+s19-event-statistics-single.xlsx,AOI 001,186
+s19-event-statistics-single.xlsx,AOI 002,61
+s21-event-statistics-single.xlsx,AOI 003,2658
+s21-event-statistics-single.xlsx,AOI 001,349
+s21-event-statistics-single.xlsx,AOI 002,26
+s23-event-statistics-single.xlsx,AOI 003,6429
+s23-event-statistics-single.xlsx,AOI 002,79
+s23-event-statistics-single.xlsx,AOI 001,2
+s24-event-statistics-single.xlsx,AOI 003,2248
+s24-event-statistics-single.xlsx,AOI 002,37
+s24-event-statistics-single.xlsx,AOI 001,24
+s25-event-statistics-single.xlsx,AOI 003,3466
+s25-event-statistics-single.xlsx,AOI 002,110
+s25-event-statistics-single.xlsx,AOI 001,101

clip_protocol-2.3/evaluation/real_frequencies.py

@@ -0,0 +1,66 @@
+import os
+import pandas as pd
+from collections import Counter
+from glob import glob
+
+def filter_databases(excel_files, field):
+    excels = []
+    for excel_file in excel_files:
+        try:
+            df_temp = pd.read_excel(excel_file)
+            if any(col.startswith("Unnamed") for col in df_temp.columns):
+                df = pd.read_excel(excel_file, header=1)  
+            else:
+                df = df_temp
+
+            matching_columns = [col for col in field if col in df.columns]
+            if not matching_columns:
+                print(f"⚠️ Ninguna de las columnas especificadas está en {excel_file}")
+                continue
+            
+            df = df[matching_columns].copy()
+            df.columns = ["value"]
+
+            df['value'] = df['value'].astype(str).apply(lambda x: x.strip())
+            df = df[df['value'] != '-']
+            df = df[df['value'].str.contains(r'\w', na=False)]
+            filename = os.path.basename(excel_file)
+
+            excels.append((df, filename))
+
+        except Exception as e:
+            print(f"❌ Error leyendo {excel_file}: {e}")
+        print(f"✅ Procesado {excel_file} correctamente.")
+    return excels
+
+def compute_real_frequencies(df: pd.DataFrame):
+    counter = Counter(df['value'])
+    freq_df = pd.DataFrame(counter.items(), columns=["Element", "Frequency"]).sort_values(by="Frequency", ascending=False)
+    return freq_df.reset_index(drop=True)
+
+if __name__ == "__main__":
+    carpeta_excel = "/Users/martajones/Downloads/Databases"
+    campos_a_contar = ["AOI Name", "AOI name", "AOI_Name"]  # por si varía el nombre
+
+    archivos_excel = glob(os.path.join(carpeta_excel, "*.xlsx"))
+    dfs = filter_databases(archivos_excel, campos_a_contar)
+
+    if not dfs:
+        print("No se han encontrado datos válidos.")
+        exit()
+
+    all_freqs = []
+    for df, filename in dfs:
+        counts = df['value'].value_counts()
+        for value, freq in counts.items():
+            all_freqs.append({
+                "Archivo": filename,
+                "Campo": value,
+                "Frecuencia": freq
+            })
+
+    df_all_freqs = pd.DataFrame(all_freqs)
+    df_all_freqs = df_all_freqs.sort_values(by=["Archivo", "Frecuencia"], ascending=[True, False])
+    df_all_freqs.to_csv("frecuencias_por_archivo.csv", index=False)
+
+

{clip_protocol-2.2.13 → clip_protocol-2.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "clip_protocol"
-version = "2.2.13"
+version = "2.3"
 authors = [
   { name="Marta Jones González", email="martajon10@gmail.com" },
 ]

{clip_protocol-2.2.13 → clip_protocol-2.3}/src/clip_protocol/main/setup.py

@@ -76,6 +76,7 @@ class Setup:
         self.df['value'] = self.df['value'].astype(str).apply(lambda x: x.strip())
         self.df = self.df[self.df['value'] != '-']
         self.df = self.df[self.df['value'].str.contains(r'\w', na=False)]
+        self.df = self.df.sample(frac=1, random_state=None).reset_index(drop=True)
         self.N = len(self.df)
     
     def run_command(self, e, k, m):

clip_protocol-2.2.13/evaluation/figures/experiment6_estimate.txt

@@ -1,213 +0,0 @@
-Enter the event to estimate or q' to quit: 
-📊 Estimated frequency of '' per user:
-
-🧑 User a5fcecb447: 6.0226
-🧑 User 7246a691b1: 0.0000
-🧑 User ac7e217530: 0.0000
-🧑 User a4d19bf287: 2.2811
-🧑 User 021112db53: 0.0000
-🧑 User 5207a4267e: 0.3976
-🧑 User 919c67db77: 0.8454
-🧑 User 3c644a1401: 0.2286
-🧑 User 88e1c85a55: 1.1747
-🧑 User 701ac89b2f: 0.0000
-🧑 User 9f59e66ff1: 0.0000
-🧑 User 6d08d55f05: 0.0000
-🧑 User 26fec0ec9d: 2.2726
-🧑 User 7641928d49: 0.0000
-🧑 User f0c8e40f51: 0.0000
-🧑 User ecff214750: 0.0000
-🧑 User 8257e18d5e: 0.0000
-🧑 User 970ee0452b: 0.0000
-🧑 User 84901f320a: 2.8722
-🧑 User 737d61a297: 0.0000
-🧑 User 183e3f200d: 1.1747
-🧑 User 4de4d32ead: 0.0000
-🧑 User 2a85807b6b: 0.0000
-🧑 User bd7fec0021: 5.9296
-🧑 User 8d99470a36: 3.3875
-🧑 User 444ca7a7d2: 3.7168
-🧑 User 013719842e: 1.5884
-🧑 User d5fe134ee2: 0.0000
-🧑 User 64a436d06c: 0.0000
-🧑 User 92e781df39: 0.0000
-🧑 User bbc60a94e1: 1.4280
-🧑 User daf4391eac: 0.0000
-🧑 User 38f6fa697b: 0.0000
-🧑 User 762c85c64e: 3.8097
-🧑 User d81be1c2f1: 0.0683
-🧑 User 17574d81d1: 0.0000
-🧑 User a7a70ff1d7: 2.3655
-🧑 User 34534ea7d2: 0.0000
-🧑 User a08f3d0564: 0.0000
-🧑 User 716e75916f: 0.0000
-🧑 User 3a36ef8b11: 4.7558
-🧑 User 8079e67204: 3.5479
-🧑 User 9e76dff829: 0.0000
-🧑 User abec3cb8ce: 0.0000
-🧑 User 749d22a2cc: 1.4366
-🧑 User 7fcf6de40f: 0.0000
-🧑 User dea36ce3cf: 0.1527
-🧑 User a6523ce7e0: 2.1036
-🧑 User f1fb300c01: 0.9128
-🧑 User 6e133b897a: 0.0000
-Enter the event to estimate or q' to quit: 
-📊 Estimated frequency of 'AOI 001' per user:
-
-🧑 User a5fcecb447: 0.0000
-🧑 User 7246a691b1: 0.0000
-🧑 User ac7e217530: 0.0000
-🧑 User a4d19bf287: 0.0000
-🧑 User 021112db53: 1.3351
-🧑 User 5207a4267e: 0.0000
-🧑 User 919c67db77: 0.0000
-🧑 User 3c644a1401: 0.0000
-🧑 User 88e1c85a55: 1.1747
-🧑 User 701ac89b2f: 0.0000
-🧑 User 9f59e66ff1: 2.0107
-🧑 User 6d08d55f05: 0.0000
-🧑 User 26fec0ec9d: 0.0597
-🧑 User 7641928d49: 0.0000
-🧑 User f0c8e40f51: 2.0363
-🧑 User ecff214750: 0.0000
-🧑 User 8257e18d5e: 0.0000
-🧑 User 970ee0452b: 0.0000
-🧑 User 84901f320a: 0.6594
-🧑 User 737d61a297: 1.5125
-🧑 User 183e3f200d: 0.0000
-🧑 User 4de4d32ead: 0.0000
-🧑 User 2a85807b6b: 8.5817
-🧑 User bd7fec0021: 2.6104
-🧑 User 8d99470a36: 0.0000
-🧑 User 444ca7a7d2: 2.6104
-🧑 User 013719842e: 0.0000
-🧑 User d5fe134ee2: 0.0000
-🧑 User 64a436d06c: 3.3875
-🧑 User 92e781df39: 0.4146
-🧑 User bbc60a94e1: 0.0000
-🧑 User daf4391eac: 0.9128
-🧑 User 38f6fa697b: 0.0000
-🧑 User 762c85c64e: 0.4905
-🧑 User d81be1c2f1: 0.0000
-🧑 User 17574d81d1: 0.0000
-🧑 User a7a70ff1d7: 1.2591
-🧑 User 34534ea7d2: 0.5835
-🧑 User a08f3d0564: 2.3570
-🧑 User 716e75916f: 2.3655
-🧑 User 3a36ef8b11: 2.5430
-🧑 User 8079e67204: 0.0000
-🧑 User 9e76dff829: 1.5125
-🧑 User abec3cb8ce: 1.8674
-🧑 User 749d22a2cc: 4.7558
-🧑 User 7fcf6de40f: 0.0000
-🧑 User dea36ce3cf: 0.0000
-🧑 User a6523ce7e0: 2.1036
-🧑 User f1fb300c01: 0.0000
-🧑 User 6e133b897a: 1.0817
-Enter the event to estimate or q' to quit: 
-📊 Estimated frequency of 'AOI 002' per user:
-
-🧑 User a5fcecb447: 0.4905
-🧑 User 7246a691b1: 0.0000
-🧑 User ac7e217530: 0.0000
-🧑 User a4d19bf287: 2.2811
-🧑 User 021112db53: 7.9735
-🧑 User 5207a4267e: 0.0000
-🧑 User 919c67db77: 0.0000
-🧑 User 3c644a1401: 5.7607
-🧑 User 88e1c85a55: 5.6003
-🧑 User 701ac89b2f: 0.9213
-🧑 User 9f59e66ff1: 0.0000
-🧑 User 6d08d55f05: 0.0000
-🧑 User 26fec0ec9d: 2.2726
-🧑 User 7641928d49: 0.0000
-🧑 User f0c8e40f51: 4.2491
-🧑 User ecff214750: 1.6899
-🧑 User 8257e18d5e: 0.0000
-🧑 User 970ee0452b: 4.6628
-🧑 User 84901f320a: 0.0000
-🧑 User 737d61a297: 0.0000
-🧑 User 183e3f200d: 0.0000
-🧑 User 4de4d32ead: 0.0000
-🧑 User 2a85807b6b: 4.1561
-🧑 User bd7fec0021: 0.0000
-🧑 User 8d99470a36: 0.0000
-🧑 User 444ca7a7d2: 0.0000
-🧑 User 013719842e: 3.8012
-🧑 User d5fe134ee2: 0.0000
-🧑 User 64a436d06c: 3.3875
-🧑 User 92e781df39: 0.0000
-🧑 User bbc60a94e1: 0.0000
-🧑 User daf4391eac: 3.1256
-🧑 User 38f6fa697b: 0.1442
-🧑 User 762c85c64e: 2.7033
-🧑 User d81be1c2f1: 0.0000
-🧑 User 17574d81d1: 0.0000
-🧑 User a7a70ff1d7: 1.2591
-🧑 User 34534ea7d2: 0.5835
-🧑 User a08f3d0564: 0.0000
-🧑 User 716e75916f: 3.4719
-🧑 User 3a36ef8b11: 0.0000
-🧑 User 8079e67204: 1.3351
-🧑 User 9e76dff829: 0.0000
-🧑 User abec3cb8ce: 0.0000
-🧑 User 749d22a2cc: 3.6494
-🧑 User 7fcf6de40f: 0.0000
-🧑 User dea36ce3cf: 0.1527
-🧑 User a6523ce7e0: 0.0000
-🧑 User f1fb300c01: 2.0192
-🧑 User 6e133b897a: 5.5073
-Enter the event to estimate or q' to quit: 
-📊 Estimated frequency of 'AOI 003' per user:
-
-🧑 User a5fcecb447: 1.5969
-🧑 User 7246a691b1: 0.0000
-🧑 User ac7e217530: 0.0000
-🧑 User a4d19bf287: 0.0683
-🧑 User 021112db53: 0.0000
-🧑 User 5207a4267e: 1.5040
-🧑 User 919c67db77: 0.0000
-🧑 User 3c644a1401: 2.4415
-🧑 User 88e1c85a55: 0.0000
-🧑 User 701ac89b2f: 4.2405
-🧑 User 9f59e66ff1: 0.0000
-🧑 User 6d08d55f05: 0.0000
-🧑 User 26fec0ec9d: 2.2726
-🧑 User 7641928d49: 1.0817
-🧑 User f0c8e40f51: 2.0363
-🧑 User ecff214750: 2.7963
-🧑 User 8257e18d5e: 0.0000
-🧑 User 970ee0452b: 2.4500
-🧑 User 84901f320a: 0.0000
-🧑 User 737d61a297: 1.5125
-🧑 User 183e3f200d: 0.0683
-🧑 User 4de4d32ead: 0.0000
-🧑 User 2a85807b6b: 0.0000
-🧑 User bd7fec0021: 1.5040
-🧑 User 8d99470a36: 0.0000
-🧑 User 444ca7a7d2: 0.0000
-🧑 User 013719842e: 2.6948
-🧑 User d5fe134ee2: 0.0000
-🧑 User 64a436d06c: 0.0683
-🧑 User 92e781df39: 0.4146
-🧑 User bbc60a94e1: 1.4280
-🧑 User daf4391eac: 3.1256
-🧑 User 38f6fa697b: 0.1442
-🧑 User 762c85c64e: 0.0000
-🧑 User d81be1c2f1: 0.0000
-🧑 User 17574d81d1: 2.6948
-🧑 User a7a70ff1d7: 3.4719
-🧑 User 34534ea7d2: 0.5835
-🧑 User a08f3d0564: 0.0000
-🧑 User 716e75916f: 0.1527
-🧑 User 3a36ef8b11: 1.4366
-🧑 User 8079e67204: 0.0000
-🧑 User 9e76dff829: 0.0000
-🧑 User abec3cb8ce: 0.0000
-🧑 User 749d22a2cc: 2.5430
-🧑 User 7fcf6de40f: 0.0000
-🧑 User dea36ce3cf: 2.3655
-🧑 User a6523ce7e0: 0.0000
-🧑 User f1fb300c01: 0.9128
-🧑 User 6e133b897a: 2.1881
-Enter the event to estimate or q' to quit: 

clip_protocol-2.2.13/evaluation/test_ks.py

@@ -1,37 +0,0 @@
-import pandas as pd
-import numpy as np
-from scipy.stats import chisquare, poisson, uniform
-
-# Carga datos
-df_5000 = pd.read_excel('datasets-article/aoi-hits-d1-3000.xlsx')
-
-df_5000['aoi_hit'] = df_5000['aoi_hit'].replace({
-    'subevent_0': 0,
-    'subevent_1': 1,
-    'subevent_2': 2,
-    'subevent_3': 3
-}).astype(int)
-
-counts = np.bincount(df_5000['aoi_hit'], minlength=4)
-#counts = [790, 1580, 1580, 1050] # para poisson
-
-print("Counts (observed):", counts)
-
-# Parámetro lambda
-lambda_poisson = 2
-
-# Calcula probabilidades Poisson para valores 0..3
-probs = poisson.pmf(np.arange(4), mu=lambda_poisson)
-#probs = uniform.pdf(np.arange(4), loc=0, scale=4)  # Distribución uniforme para 0..3
-
-# Normaliza para que sumen 1 solo en esos valores
-probs = probs / probs.sum()
-
-# Calcula esperados según la distribución teórica
-expected = probs * sum(counts)
-
-# Test chi-cuadrado
-stat, pvalue = chisquare(counts, f_exp=expected)
-
-print(f"Chi2 statistic: {stat:.4f}")
-print(f"P-value: {pvalue:.4f}")