results_to_csv script

code/vizualisation/results_to_csv.py

+from pathlib import Path
+import os
+import pandas as pd
+from pprint import pprint
+import pickle
+from collections import defaultdict
+
+from dotenv import load_dotenv, find_dotenv
+
+
+dct_experiment_id_subset = dict((str(idx), "train+dev/train+dev") for idx in range(1, 9))
+dct_experiment_id_subset.update(dict((str(idx), "train/dev") for idx in range(9, 17)))
+
+dct_experiment_id_technique = {"1": 'None',
+                               "2": 'Random',
+                               "3": 'OMP',
+                               "4": 'OMP Distillation',
+                               "5": 'Kmeans',
+                               "6": 'Zhang Similarities',
+                               "7": 'Zhang Predictions',
+                               "8": 'Ensemble',
+                               "9": 'None',
+                               "10": 'Random',
+                               "11": 'OMP',
+                               "12": 'OMP Distillation',
+                               "13": 'Kmeans',
+                               "14": 'Zhang Similarities',
+                               "15": 'Zhang Predictions',
+                               "16": 'Ensemble'
+                               }
+
+
+dct_dataset_fancy = {
+    "boston": "Boston",
+    "breast_cancer": "Breast Cancer",
+    "california_housing": "California Housing",
+    "diabetes": "Diabetes",
+    "diamonds": "Diamonds",
+    "digits": "Digits",
+    "iris": "Iris",
+    "kin8nm": "Kin8nm",
+    "kr-vs-kp": "KR-VS-KP",
+    "olivetti_faces": "Olivetti Faces",
+    "spambase": "Spambase",
+    "steel-plates": "Steel Plates",
+    "wine": "Wine",
+    "gamma": "Gamma",
+    "lfw_pairs": "LFW Pairs"
+}
+
+skip_attributes = ["datetime", "model_weights"]
+
+
+if __name__ == "__main__":
+
+    load_dotenv(find_dotenv('.env'))
+    dir_name = "results/bolsonaro_models_25-03-20"
+    dir_path = Path(os.environ["project_dir"]) / dir_name
+
+    output_dir_file = dir_path / "results.csv"
+
+    dct_results = defaultdict(lambda: [])
+
+    for root, dirs, files in os.walk(dir_path, topdown=False):
+        for file_str in files:
+            path_dir = Path(root)
+            path_file = path_dir / file_str
+            obj_results = pickle.load(open(path_file, 'rb'))
+
+            path_dir_split = str(path_dir).split("/")
+
+            bool_wo_weights = "no_weights" in str(path_file)
+
+            if bool_wo_weights:
+                forest_size = int(path_dir_split[-1].split("_")[0])
+            else:
+                forest_size = int(path_dir_split[-1])
+
+            seed = int(path_dir_split[-3])
+            id_xp = str(path_dir_split[-5])
+            dataset = str(path_dir_split[-6])
+
+            dct_results["forest_size"].append(forest_size)
+            dct_results["seed"].append(seed)
+            dct_results["dataset"].append(dct_dataset_fancy[dataset])
+            dct_results["subset"].append(dct_experiment_id_subset[id_xp])
+            dct_results["strategy"].append(dct_experiment_id_technique[id_xp])
+            dct_results["wo_weights"].append(bool_wo_weights)
+
+            for key_result, val_result in obj_results.items():
+                if key_result in skip_attributes:
+                    continue
+                if val_result == "":
+                    val_result = None
+                dct_results[key_result].append(val_result)
+
+            print(path_file)
+
+
+    final_df = pd.DataFrame.from_dict(dct_results)
+    final_df.to_csv(output_dir_file)
+    print(final_df)