add converted NAB dataset and conversion script

Former-commit-id: e5e471b7d4 [formerly d2ab1ee11d] [formerly d35d6343cb [formerly a56625c5c6]] [formerly cdc12895a6 [formerly b777341b1c] [formerly a1e643e776 [formerly 7b4fa4725f]]] [formerly cfc417417c [formerly 751bcb7b26] [formerly 9ad526bd55 [formerly bafa08fede]] [formerly ffc89cb24f [formerly 9f869a68ba] [formerly 4a198b127f [formerly 8680466e3e]]]] [formerly 313dac8796 [formerly 21c9ad0874] [formerly 9cca83ab86 [formerly 5d27f72aba]] [formerly 46639b7c2f [formerly 6660c22c45] [formerly 1d55be3b65 [formerly 47d15a1450]]] [formerly 37da483cd0 [formerly 573d2f3058] [formerly cc50743d1d [formerly af59ba6862]] [formerly 7c285c8af2 [formerly 030f2b7705] [formerly 6992119074 [formerly f30ea9c340]]]]] [formerly 11ef3614df [formerly 311d96d17a] [formerly 8566aab3e0 [formerly c3665a4790]] [formerly f86ecf51b7 [formerly a9f031ba64] [formerly c1afd9ab93 [formerly 84a48e34dd]]] [formerly 5255524a8a [formerly 915b93002d] [formerly 2ee6633d23 [formerly 7fb8e14f42]] [formerly f994d0ffc3 [formerly 4a3fdb5e64] [formerly b5f78ca944 [formerly b0b98ea772]]]] [formerly 8eb76f3579 [formerly ec80650a7e] [formerly 312076f5a9 [formerly 474a5e8b78]] [formerly 72335861cd [formerly c4d2734474] [formerly 5f2cadc521 [formerly c94de5eac5]]] [formerly b444ea2bc4 [formerly 51c43c812a] [formerly 9387478d2d [formerly fcef93319c]] [formerly ebc58c38b0 [formerly aba49eb6b6] [formerly 15c4982f4a [formerly 59879a8fa6]]]]]]
Former-commit-id: 5fddd9dd13 [formerly ca628cbc97] [formerly f75e7b129c [formerly 594cd370b9]] [formerly adedf60df9 [formerly 83f5695380] [formerly ea0fa87783 [formerly 4181f5be7a]]] [formerly de4631fef5 [formerly dcf897a5ce] [formerly 93abd01da9 [formerly 9164adba2e]] [formerly 1ae70b26b6 [formerly 5d3413b8d5] [formerly 85ae54ab6a [formerly 422262c562]]]] [formerly 25705cf39f [formerly afc818f4ff] [formerly 6dc2dd6f6d [formerly 0f54f5aac7]] [formerly 15ce462878 [formerly c7a9faef04] [formerly 98cda6c05b [formerly e8e25570a8]]] [formerly 1489696317 [formerly 1be1f71c96] [formerly fc45e064b5 [formerly 4bc136dade]] [formerly 6124e22c63 [formerly aa8152f8f0] [formerly 15c4982f4a]]]]
Former-commit-id: 46eb3bf841 [formerly bec16dc890] [formerly fcd7030d56 [formerly 06d5db40fd]] [formerly 586eb86b80 [formerly 8bc54e9527] [formerly bacd866069 [formerly 2057c06d09]]] [formerly da7bac8e62 [formerly 053ce9b44d] [formerly 4e6e7861ae [formerly caee5a67ed]] [formerly eb9d20ee6b [formerly 5466bbdb9a] [formerly ef2a8c6f20 [formerly faccf9b092]]]]
Former-commit-id: f958cd0610 [formerly d295b88e0b] [formerly b435efd2f1 [formerly 6dcaedaf4a]] [formerly da8c8a7ab6 [formerly 1aba37dd2b] [formerly 6306969c21 [formerly 8d5738b76d]]]
Former-commit-id: 6b65432bea [formerly 3b2b18765e] [formerly b8eb99fe4f [formerly c5360af891]]
Former-commit-id: b4d7cbe3af [formerly b9e256f2a3]
Former-commit-id: 150a5d86cd

datasets/NAB/add_label.py

@@ -1,6 +1,9 @@
 
 import pandas as pd
 import json
+import os
+import time
+import datetime
 
 
 label_file = open('combined_labels.json', 'r')
@@ -10,11 +13,16 @@ for key in label_info.keys():
     df = pd.read_csv(key) 
     fpath, fname = key.split('/')[0], key.split('/')[1]
     label = []
+    unix_timestamp = []
     for _, row in df.iterrows():
         if row['timestamp'] in list(label_info[key]):
             label.append('1')
         else:
             label.append('0')
+        timestamp = datetime.datetime.strptime(row['timestamp'], '%Y-%m-%d %H:%M:%S').timestamp()
+        unix_timestamp.append(timestamp)
     df['label'] = label
+    df['timestamp'] = unix_timestamp
     df.to_csv(fpath+"/labeled_"+fname, index=False)
+    #os.remove(key)
 

datasets/NAB/realKnownCause/labeled_cpu_utilization_asg_misconfiguration.csv.REMOVED.git-id

@@ -1 +1 @@
-6b0bc2aa98d9bd1769aded1842269293ecdbf46c
+948611b07519538ef036e0ec1c948f6bf97009cf

datasets/NAB/realKnownCause/labeled_machine_temperature_system_failure.csv.REMOVED.git-id

@@ -1 +1 @@
-4e6e62763fb4d8a5c8ca35981b7af97c9ce88fbc
+428229640a5466e68014f74649a24f00abb1150b

datasets/NAB/realKnownCause/labeled_nyc_taxi.csv.REMOVED.git-id

@@ -1 +0,0 @@
-8d535c4e4624c3e769c603db381cde74ffd1541b

datasets/NAB/realTweets/labeled_Twitter_volume_AAPL.csv.REMOVED.git-id

@@ -1 +1 @@
-0edff7c15786fd853fe6ad350c614242f5b2871b
+68dd1084ed091fb9affe45b4e0894250c6c62c07

datasets/NAB/realTweets/labeled_Twitter_volume_AMZN.csv.REMOVED.git-id

@@ -1 +1 @@
-8cb8dcfaa5c9c855e7c6d4f059838e20284d6dbc
+7bebf0fe077dda56f789d644090faf1d2484913c

datasets/NAB/realTweets/labeled_Twitter_volume_CRM.csv.REMOVED.git-id

@@ -1 +1 @@
-f813962b33568d076285707a60cbfec7b0daa864
+59fdf3c2b8d171704e3de1e10d8ccfca72c8ab9a

datasets/NAB/realTweets/labeled_Twitter_volume_CVS.csv.REMOVED.git-id

@@ -1 +1 @@
-5a221a242b60a8ff302a6bf174ab05b7661a1dfd
+d20453833fc13c681f0b5f5a830f3aba52b774cd

datasets/NAB/realTweets/labeled_Twitter_volume_FB.csv.REMOVED.git-id

@@ -1 +1 @@
-da6e1f36aeba57d81340b3e468a64eca017561f0
+ed60bba6f53c779335874c39966b7d5e4309e2c3

datasets/NAB/realTweets/labeled_Twitter_volume_GOOG.csv.REMOVED.git-id

@@ -1 +1 @@
-a2b7ee363323c1583a38fc604425281d0a32e90a
+f01b654d9a6a6ebc7efc65da240f83680de2131d

datasets/NAB/realTweets/labeled_Twitter_volume_IBM.csv.REMOVED.git-id

@@ -1 +1 @@
-4c504cb93885a3d759c308d39833af0cb72586b8
+8e0088d97641d6ab39b808fe03ac0a7ec9ea99b9

datasets/NAB/realTweets/labeled_Twitter_volume_KO.csv.REMOVED.git-id

@@ -1 +1 @@
-3e208a1d5a72f93d3105599578918e51f07a31f1
+d72fffb08da82bb70ecc379bb1fa56316efda557

datasets/NAB/realTweets/labeled_Twitter_volume_PFE.csv.REMOVED.git-id

@@ -1 +1 @@
-3147689c7a7ae3b0b05a5ee2de699f754e8973e9
+4c2f8543201c0a66e44815dee128d9044a41c382

datasets/NAB/realTweets/labeled_Twitter_volume_UPS.csv.REMOVED.git-id

@@ -1 +1 @@
-3e4904fb5fa4e4c0b86fc67f1700b94786f376f5
+25a0dd3110986418d379a887cc575f9fdc45a6da

examples/run_automl.py

@@ -7,7 +7,7 @@ from tods.search import BruteForceSearch
 
 # Some information
 table_path = 'datasets/NAB/realTweets/labeled_Twitter_volume_IBM.csv' # The path of the dataset
-target_index = 3 # what column is the target
+target_index = 2 # what column is the target
 
 #table_path = 'datasets/yahoo_sub_5.csv'
 #target_index = 6 # what column is the target

tods/tods/search/brute_force_search.py

@@ -57,14 +57,14 @@ class BruteForceSearch(PipelineSearchBase):
 
         # DEBUG
         ####################
-        #for pipeline_result in pipeline_results:
-        #    try:
-        #        for error in pipeline_result.error:
-        #            if error is not None:
-        #                raise error
-        #    except:
-        #        import traceback
-        #        traceback.print_exc()
+        for pipeline_result in pipeline_results:
+            try:
+                for error in pipeline_result.error:
+                    if error is not None:
+                        raise error
+            except:
+                import traceback
+                traceback.print_exc()
         ####################
 
         return [self.ranking_function(pipeline_result) for pipeline_result in pipeline_results]