a

datasets/alpi/__init__.py

@@ -121,6 +121,7 @@ def create_params_list(data_path, params, verbose=True):
 
 # PHASE 1
 
+
 # current_offset must be an integer and it must indicate minutes
 def generate_dataset_by_serial_offset(data, params, current_offset):
     data["current_offset"] = current_offset

datasets/alpi/dataset.py

@@ -121,6 +121,7 @@ def create_params_list(data_path, params, verbose=True):
 
 # PHASE 1
 
+
 # current_offset must be an integer and it must indicate minutes
 def generate_dataset_by_serial_offset(data, params, current_offset):
     data["current_offset"] = current_offset

datasets/cbm/__init__.py

@@ -7,7 +7,6 @@
 
 
 def parse_feature_names(fn):
-
     with open(fn) as f:
         names, lines = [], f.readlines()
         for line in lines:
@@ -17,7 +16,6 @@ def parse_feature_names(fn):
 
 
 def load_data(shorten_feature_names=True):
-
     fp = os.path.dirname(__file__)
     raw_data = np.loadtxt(fp + "/data.txt.gz")
     features = parse_feature_names(fp + "/Features.txt")
@@ -51,7 +49,6 @@ def load_clean_data():
 
 
 def gen_summary(wd=400, outdir=None):
-
     if outdir is None:
         outdir = os.path.dirname(__file__)
 

datasets/cmapss/__init__.py

@@ -2,6 +2,7 @@
 import numpy as np
 import pandas as pd
 import tqdm
+
 # from sklearn.model_selection import train_test_split
 from sklearn.model_selection import KFold
 
@@ -86,13 +87,21 @@ def load_clean_data_rul(
 ):
     train, test, labels = load_mesurement_list(index=index, features=features)
     label = "RUL"
+    class_label_name = "Class"
+    if index=="FD001" or index=="FD002":
+        class_=1
+    elif index=="FD003" or index=="FD004":
+        class_=2
+    else:
+        class_=0
 
     # train
     train_df_list = []
     for tt in train:
         max_rul = len(tt)
         rul_array = np.array(range(max_rul))[::-1]
         tt[label] = rul_array
+        tt[class_label_name] = class_
         train_df_list.append(tt)
 
     # test
@@ -102,38 +111,55 @@ def load_clean_data_rul(
         rul_array = np.array(range(max_rul))[::-1]
         rul_array += int(la)
         tt[label] = rul_array
+        tt[class_label_name] = class_
         test_df_list.append(tt)
 
     return train_df_list, test_df_list
 
 
 def load_clean_data_rul_k_folds(
     split_ind,
-    indices=["FD004",],
+    indices=[
+        "FD004",
+    ],
     k=5,
     features=[2, 3, 4, 7, 11, 12, 15],
     random_state=0,
+    use_test=True,
+    val=0.1,
 ):
     df_list = []
     for index in indices:
-        train_df_list, test_df_list = load_clean_data_rul(index=index, features=features,)
+        train_df_list, test_df_list = load_clean_data_rul(
+            index=index,
+            features=features,
+        )
         df_list.extend(train_df_list)
-        df_list.extend(test_df_list)
-
+        if use_test:
+            df_list.extend(test_df_list)
+
     data_index = range(len(df_list))
-    
+
     kf = KFold(
         n_splits=k,
         random_state=random_state,
-        shuffle=True,)
+        shuffle=True,
+    )
 
-    train_idx,test_idx = list(kf.split(data_index))[split_ind]
+    train_idx, test_idx = list(kf.split(data_index))[split_ind]
+    len(train_idx)
+    print(f"all index:{len(data_index)}")
+    print(train_idx)
+    print(test_idx)
 
     new_train_df_list = [df_list[i] for i in train_idx]
     new_test_df_list = [df_list[i] for i in test_idx]
 
     return new_train_df_list, new_test_df_list
 
+
+
+
 def load_mesurement_list(
     index="FD004",
     features=[2, 3, 4, 7, 11, 12, 15],
@@ -168,7 +194,6 @@ def load_mesurement_list(
 
 
 def run_to_failure_aux(df, lifetime, unit_number):
-
     assert lifetime <= df.shape[0]
     broken = 0 if lifetime < df.shape[0] else 1
     sample = pd.DataFrame(
@@ -187,7 +212,6 @@ def run_to_failure_aux(df, lifetime, unit_number):
 
 
 def censoring_augmentation(raw_data, n_samples=10, seed=123):
-
     np.random.seed(seed)
     datasets = [g for _, g in raw_data.groupby("unit_number")]
     timeseries = raw_data.groupby("unit_number").size()
@@ -206,7 +230,6 @@ def censoring_augmentation(raw_data, n_samples=10, seed=123):
 
 
 def generate_run_to_failure(df, health_censor_aug=0, seed=123):
-
     samples = []
     for unit_id, timeseries in tqdm.tqdm(df.groupby("unit_number"), desc="RUL"):
         samples.append(run_to_failure_aux(timeseries, timeseries.shape[0], unit_id))
@@ -227,7 +250,6 @@ def leave_one_out(
     input_fn=None,
     output_fn=None,
 ):
-
     if input_fn is not None:
         subsets = pd.read_csv(input_fn)
 

datasets/gdd/__init__.py

@@ -7,7 +7,6 @@
 
 
 def load_data(index="state"):
-
     assert index in ["state", "anomaly", "normal", "linear", "pressure"]
     fp = os.path.dirname(__file__)
 
@@ -163,15 +162,13 @@ def plot_genesis_nonlabels(df, figsize=(15, 20), cmap="tab10"):
 
 
 def gen_summary(outdir=None):
-
     if outdir is None:
         outdir = os.path.dirname(__file__)
 
     os.makedirs(outdir, exist_ok=True)
     sns.set(font_scale=1.1, style="whitegrid")
 
     with PdfPages(outdir + "/gdd_summary.pdf") as pp:
-
         print("Plotting Genesis_StateMachineLabel...")
         df = load_data(index="state")
         fig, _ = plot_genesis_labels(df)

datasets/gfd/__init__.py

@@ -44,7 +44,6 @@ def plot_sequence(df, st=0, ed=None, ax=None, figsize=(10, 3), individual=True):
 
 
 def gen_summary(outdir=None, st=0, ed=500, wd=20, hg=8):
-
     if outdir is None:
         outdir = os.path.dirname(__file__)
 

datasets/hydsys/__init__.py

@@ -5,7 +5,6 @@
 
 
 def load_data(sensor=None, rw=0):
-
     if sensor is None:
         # load full data
         # rw is ignored to concatenate all sensor data
@@ -21,7 +20,6 @@ def load_data(sensor=None, rw=0):
 
 
 def load_sensor_data(sensor, rw=0):
-
     data = []
     sensor_list = get_sensor_list(sensor)
     fp = os.path.dirname(__file__)