diff --git a/code/playground/nn_omp.py b/code/playground/nn_omp.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/code/vizualisation/csv_to_figure.py b/code/vizualisation/csv_to_figure.py
index 73b990f363b8e65a97e7c6a91c6b304a199e3034..244314ba9fcbb49ab48762c09dd63e4d69df9cf5 100644
--- a/code/vizualisation/csv_to_figure.py
+++ b/code/vizualisation/csv_to_figure.py
@@ -9,15 +9,15 @@ import plotly.io as pio
lst_skip_strategy = ["None", "OMP Distillation", "OMP Distillation w/o weights"]
# lst_skip_subset = ["train/dev"]
-lst_skip_subset = []
+lst_task_train_dev = ["coherence", "correlation"]
tasks = [
# "train_score",
# "dev_score",
# "test_score",
- # "coherence",
- # "correlation",
- "negative-percentage"
+ "coherence",
+ "correlation",
+ # "negative-percentage"
]
dct_score_metric_fancy = {
@@ -98,83 +98,75 @@ if __name__ == "__main__":
df_data = df_results[df_results["dataset"] == data_name]
score_metric_name = df_data["score_metric"].values[0]
- for subset_name in subsets:
- if subset_name in lst_skip_subset:
- continue
- df_subset = df_data[df_data["subset"] == subset_name]
- fig = go.Figure()
-
- ##################
- # all techniques #
- ##################
- for strat in strategies:
- if strat in lst_skip_strategy:
- continue
- df_strat = df_subset[df_subset["strategy"] == strat]
-
- if "OMP" in strat:
- ###########################
- # traitement avec weights #
- ###########################
- df_strat_wo_weights = df_strat[df_strat["wo_weights"] == False]
- if data_name == "Boston" and subset_name == "train+dev/train+dev":
- df_strat_wo_weights = df_strat_wo_weights[df_strat_wo_weights["forest_size"] < 400]
- add_trace_from_df(df_strat_wo_weights, fig)
-
- if "OMP" in strat and subset_name == "train/dev":
- continue
- elif "Random" not in strat and subset_name == "train/dev":
- continue
-
- #################################
- # traitement general wo_weights #
- #################################
- if "Random" in strat:
- df_strat_wo_weights = df_strat[df_strat["wo_weights"] == False]
- else:
- df_strat_wo_weights = df_strat[df_strat["wo_weights"] == True]
-
- if "OMP" in strat:
- strat = "{} w/o weights".format(strat)
+ fig = go.Figure()
+ ##################
+ # all techniques #
+ ##################
+ for strat in strategies:
+ if strat in lst_skip_strategy:
+ continue
+ df_strat = df_data[df_data["strategy"] == strat]
+ df_strat = df_strat[df_strat["subset"] == "train+dev/train+dev"]
+
+ if "OMP" in strat:
+ ###########################
+ # traitement avec weights #
+ ###########################
+ df_strat_wo_weights = df_strat[df_strat["wo_weights"] == False]
+ if data_name == "Boston":
+ df_strat_wo_weights = df_strat_wo_weights[df_strat_wo_weights["forest_size"] < 400]
add_trace_from_df(df_strat_wo_weights, fig)
- title = "{} {} {}".format(task, data_name, subset_name)
- yaxis_title = "% negative weights" if task == "negative-percentage" else dct_score_metric_fancy[score_metric_name]
- fig.update_layout(barmode='group',
- title=title,
- xaxis_title="# Selected Trees",
- yaxis_title=yaxis_title,
+ #################################
+ # traitement general wo_weights #
+ #################################
+ if "OMP" in strat:
+ df_strat_wo_weights = df_strat[df_strat["wo_weights"] == True]
+ else:
+ df_strat_wo_weights = df_strat[df_strat["wo_weights"] == False]
+
+ if "OMP" in strat:
+ strat = "{} w/o weights".format(strat)
+
+ add_trace_from_df(df_strat_wo_weights, fig)
+
+ title = "{} {}".format(task, data_name)
+ yaxis_title = "% negative weights" if task == "negative-percentage" else dct_score_metric_fancy[score_metric_name]
+ fig.update_layout(barmode='group',
+ title=title,
+ xaxis_title="# Selected Trees",
+ yaxis_title=yaxis_title,
+ font=dict(
+ # family="Courier New, monospace",
+ size=24,
+ color="black"
+ ),
+ showlegend = False,
+ margin = dict(
+ l=1,
+ r=1,
+ b=1,
+ t=1,
+ # pad=4
+ ),
+ legend=dict(
+ traceorder="normal",
font=dict(
- # family="Courier New, monospace",
+ family="sans-serif",
size=24,
color="black"
),
- showlegend = False,
- margin = dict(
- l=1,
- r=1,
- b=1,
- t=1,
- # pad=4
- ),
- legend=dict(
- traceorder="normal",
- font=dict(
- family="sans-serif",
- size=24,
- color="black"
- ),
- # bgcolor="LightSteelBlue",
- # bordercolor="Black",
- borderwidth=1,
- )
- )
- # fig.show()
- sanitize = lambda x: x.replace(" ", "_").replace("/", "_").replace("+", "_")
- filename = sanitize(title)
- output_dir = out_dir / sanitize(subset_name) / sanitize(task)
- output_dir.mkdir(parents=True, exist_ok=True)
- fig.write_image(str((output_dir / filename).absolute()) + ".png")
-
- # exit()
+ # bgcolor="LightSteelBlue",
+ # bordercolor="Black",
+ borderwidth=1,
+ )
+ )
+ # fig.show()
+ sanitize = lambda x: x.replace(" ", "_").replace("/", "_").replace("+", "_")
+ filename = sanitize(title)
+ output_dir = out_dir / sanitize(task)
+ output_dir.mkdir(parents=True, exist_ok=True)
+ fig.write_image(str((output_dir / filename).absolute()) + ".png")
+
+ # exit()
diff --git a/code/vizualisation/csv_to_table.py b/code/vizualisation/csv_to_table.py
index 9547361f311ea1f0c9bb61b9f2454e26a2f8650a..440e5fc8454732e40af3cce667a04d4677d032af 100644
--- a/code/vizualisation/csv_to_table.py
+++ b/code/vizualisation/csv_to_table.py
@@ -77,7 +77,7 @@ dct_data_metric = {
def get_max_from_df(df, best_fct):
- nb_to_consider = 30
+ nb_to_consider = 10
df.sort_values(by="forest_size", inplace=True)
df_groupby_forest_size = df.groupby(['forest_size'])
forest_sizes = list(df_groupby_forest_size["forest_size"].mean().values)[:nb_to_consider]
@@ -292,6 +292,8 @@ if __name__ == "__main__":
print("\\midrule")
if idx_lin == 6:
print("\\midrule")
+ if lst_data_ordered[idx_lin-1] == "Diamonds":
+ print("%", end="")
line_print = " ".join(list(lin))
line_print = line_print.rstrip(" &") + "\\\\"
print(line_print)
diff --git a/code/vizualisation/results_to_csv.py b/code/vizualisation/results_to_csv.py
index 1def6e62935debd9405900c721a1b29b45a2b8cb..669451b1f812f7f83584670790196601f1a5f40e 100644
--- a/code/vizualisation/results_to_csv.py
+++ b/code/vizualisation/results_to_csv.py
@@ -77,8 +77,10 @@ if __name__ == "__main__":
continue
path_dir = Path(root)
path_file = path_dir / file_str
+ print(path_file)
try:
- obj_results = pickle.load(open(path_file, 'rb'))
+ with open(path_file, 'rb') as pickle_file:
+ obj_results = pickle.load(pickle_file)
except:
print("problem loading pickle file {}".format(path_file))
@@ -118,6 +120,7 @@ if __name__ == "__main__":
percentage_lt_zero = nb_lt_zero / (nb_gt_zero + nb_lt_zero)
dct_results["negative-percentage"].append(percentage_lt_zero)
if val_result == "":
+ # print(key_result, val_result)
val_result = None
if key_result == "coherence" and val_result is None:
set_no_coherence.add(id_xp)