Skip to content

Commit

Permalink
Fix column list for condition description (#61)
Browse files Browse the repository at this point in the history 
Fix column list for condition description
  • Loading branch information
@christinedraper
christinedraper authored May 3, 2024
1 parent 5e7d121 commit 9d8dcfd
Show file tree
Hide file tree
Showing 3 changed files with 106 additions and 89 deletions.
64 changes: 32 additions & 32 deletions examples/example_notebooks/customized_diagnoser.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -23,8 +23,8 @@
"name": "#%%\n"
},
"ExecuteTime": {
"end_time": "2024-05-03T02:03:15.122705Z",
"start_time": "2024-05-03T02:03:15.119284Z"
"end_time": "2024-05-03T20:44:40.525488Z",
"start_time": "2024-05-03T20:44:40.522741Z"
}
},
"outputs": [],
Expand All @@ -51,8 +51,8 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-05-03T02:03:31.740325Z",
"start_time": "2024-05-03T02:03:15.137102Z"
"end_time": "2024-05-03T20:44:48.257815Z",
"start_time": "2024-05-03T20:44:40.549686Z"
}
},
"outputs": [],
Expand Down Expand Up @@ -88,8 +88,8 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-05-03T02:03:32.055442Z",
"start_time": "2024-05-03T02:03:31.743114Z"
"end_time": "2024-05-03T20:44:48.555773Z",
"start_time": "2024-05-03T20:44:48.259295Z"
}
},
"outputs": [],
Expand All @@ -113,8 +113,8 @@
"execution_count": 4,
"metadata": {
"ExecuteTime": {
"end_time": "2024-05-03T02:03:32.690456Z",
"start_time": "2024-05-03T02:03:32.056136Z"
"end_time": "2024-05-03T20:44:48.967016Z",
"start_time": "2024-05-03T20:44:48.556657Z"
}
},
"outputs": [
Expand Down Expand Up @@ -147,8 +147,8 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-05-03T02:03:33.421897Z",
"start_time": "2024-05-03T02:03:32.692755Z"
"end_time": "2024-05-03T20:44:49.668954Z",
"start_time": "2024-05-03T20:44:48.968682Z"
}
},
"outputs": [
Expand Down Expand Up @@ -185,8 +185,8 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-05-03T02:03:33.427628Z",
"start_time": "2024-05-03T02:03:33.422561Z"
"end_time": "2024-05-03T20:44:49.675298Z",
"start_time": "2024-05-03T20:44:49.669786Z"
}
},
"outputs": [
Expand Down Expand Up @@ -217,8 +217,8 @@
"execution_count": 7,
"metadata": {
"ExecuteTime": {
"end_time": "2024-05-03T02:03:33.431118Z",
"start_time": "2024-05-03T02:03:33.428470Z"
"end_time": "2024-05-03T20:44:49.678419Z",
"start_time": "2024-05-03T20:44:49.676141Z"
}
},
"outputs": [
Expand Down Expand Up @@ -250,8 +250,8 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-05-03T02:03:33.434461Z",
"start_time": "2024-05-03T02:03:33.432056Z"
"end_time": "2024-05-03T20:44:49.681587Z",
"start_time": "2024-05-03T20:44:49.679132Z"
}
},
"outputs": [
Expand Down Expand Up @@ -283,14 +283,14 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-05-03T02:03:33.623760Z",
"start_time": "2024-05-03T02:03:33.435077Z"
"end_time": "2024-05-03T20:44:49.878456Z",
"start_time": "2024-05-03T20:44:49.682343Z"
}
},
"outputs": [
{
"data": {
"text/plain": "Analyzer(metadata=Metadata(version=2, schemaVersion=1, updatedTimestamp=1714699900837, author='user_c9292ec40407f7b580f0a2c90745ebfba2b9e6ea81c848ef944d31e48a45f98', description=None), id='frequent-items-drift-analyzer-x2hr9z', displayName=None, tags=None, schedule=FixedCadenceSchedule(type='fixed', cadence=<Cadence.daily: 'daily'>, exclusionRanges=None), disabled=None, disableTargetRollup=None, targetMatrix=ColumnMatrix(segments=[Segment(tags=[])], type=<TargetLevel.column: 'column'>, include=[<ColumnGroups.group_discrete: 'group:discrete'>], exclude=[<ColumnGroups.group_output: 'group:output'>, 'desc', 'issue_d', 'url'], profileId=None), dataReadinessDuration=None, batchCoolDownPeriod=None, backfillGracePeriodDuration=None, config=DriftConfig(schemaVersion=None, params=None, metric=<ComplexMetrics.frequent_items: 'frequent_items'>, type=<AlgorithmType.drift: 'drift'>, algorithm='hellinger', threshold=0.7, minBatchSize=1, baseline=TrailingWindowBaseline(datasetId=None, inheritSegment=None, type=<BaselineType.TrailingWindow: 'TrailingWindow'>, size=7, offset=None, exclusionRanges=None)))"
"text/plain": "Analyzer(metadata=Metadata(version=6, schemaVersion=1, updatedTimestamp=1714769079201, author='user_c9292ec40407f7b580f0a2c90745ebfba2b9e6ea81c848ef944d31e48a45f98', description=None), id='frequent-items-drift-analyzer-x2hr9z', displayName=None, tags=None, schedule=FixedCadenceSchedule(type='fixed', cadence=<Cadence.daily: 'daily'>, exclusionRanges=None), disabled=None, disableTargetRollup=None, targetMatrix=ColumnMatrix(segments=[Segment(tags=[])], type=<TargetLevel.column: 'column'>, include=[<ColumnGroups.group_discrete: 'group:discrete'>], exclude=['issue_d', <ColumnGroups.group_output: 'group:output'>, 'desc', 'url'], profileId=None), dataReadinessDuration=None, batchCoolDownPeriod=None, backfillGracePeriodDuration=None, config=DriftConfig(schemaVersion=None, params=None, metric=<ComplexMetrics.frequent_items: 'frequent_items'>, type=<AlgorithmType.drift: 'drift'>, algorithm='hellinger', threshold=0.7, minBatchSize=1, baseline=TrailingWindowBaseline(datasetId=None, inheritSegment=None, type=<BaselineType.TrailingWindow: 'TrailingWindow'>, size=7, offset=None, exclusionRanges=None)))"
},
"execution_count": 9,
"metadata": {},
Expand All @@ -316,8 +316,8 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-05-03T02:03:33.839587Z",
"start_time": "2024-05-03T02:03:33.624489Z"
"end_time": "2024-05-03T20:44:50.042989Z",
"start_time": "2024-05-03T20:44:49.879144Z"
}
},
"outputs": [
Expand Down Expand Up @@ -354,8 +354,8 @@
"execution_count": 11,
"metadata": {
"ExecuteTime": {
"end_time": "2024-05-03T02:03:33.846498Z",
"start_time": "2024-05-03T02:03:33.842929Z"
"end_time": "2024-05-03T20:44:50.047697Z",
"start_time": "2024-05-03T20:44:50.045178Z"
}
},
"outputs": [
Expand Down Expand Up @@ -386,8 +386,8 @@
"execution_count": 12,
"metadata": {
"ExecuteTime": {
"end_time": "2024-05-03T02:03:33.988624Z",
"start_time": "2024-05-03T02:03:33.847364Z"
"end_time": "2024-05-03T20:44:50.203811Z",
"start_time": "2024-05-03T20:44:50.048446Z"
}
},
"outputs": [
Expand Down Expand Up @@ -419,8 +419,8 @@
"execution_count": 13,
"metadata": {
"ExecuteTime": {
"end_time": "2024-05-03T02:03:33.992473Z",
"start_time": "2024-05-03T02:03:33.989400Z"
"end_time": "2024-05-03T20:44:50.207865Z",
"start_time": "2024-05-03T20:44:50.204706Z"
}
},
"outputs": [
Expand Down Expand Up @@ -450,8 +450,8 @@
"execution_count": 14,
"metadata": {
"ExecuteTime": {
"end_time": "2024-05-03T02:03:38.883541Z",
"start_time": "2024-05-03T02:03:33.993121Z"
"end_time": "2024-05-03T20:44:54.750266Z",
"start_time": "2024-05-03T20:44:50.208637Z"
}
},
"outputs": [],
Expand All @@ -467,8 +467,8 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-05-03T02:03:38.892248Z",
"start_time": "2024-05-03T02:03:38.884434Z"
"end_time": "2024-05-03T20:44:54.758004Z",
"start_time": "2024-05-03T20:44:54.751369Z"
}
},
"outputs": [
Expand Down Expand Up @@ -505,7 +505,7 @@
"\n",
"Conditions that may contribute to noise include:\n",
"\t* Condition changing_discrete (many values are unique across batches) for 3 columns: ['desc', 'issue_d', 'url']\n",
"\t* Condition small_nonnull_batches (less than 500 non-null records in 50% or more of the batches) for 4 columns: ['desc', 'issue_d', 'url', 'desc']\n",
"\t* Condition small_nonnull_batches (less than 500 non-null records in 50% or more of the batches) for 1 columns: ['desc']\n",
"\n",
"Anomalies for columns with these conditions:\n",
"| | 0 |\n",
Expand Down
Loading

0 comments on commit 9d8dcfd

Please sign in to comment.