forked from andrew-yuhochi/ChatBot
-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
f0b0e0f
commit cff6e1a
Showing
30 changed files
with
416 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1 @@ | ||
| {"splits": ["train", "validation", "test"]} |
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,50 @@ | ||
| { | ||
| "builder_name": null, | ||
| "citation": "", | ||
| "config_name": null, | ||
| "dataset_size": null, | ||
| "description": "", | ||
| "download_checksums": null, | ||
| "download_size": null, | ||
| "features": { | ||
| "Domain": { | ||
| "dtype": "string", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "Sub domain": { | ||
| "dtype": "string", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "Intent": { | ||
| "dtype": "string", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "value": { | ||
| "dtype": "string", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "labels": { | ||
| "feature": { | ||
| "dtype": "int64", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "length": -1, | ||
| "id": null, | ||
| "_type": "Sequence" | ||
| } | ||
| }, | ||
| "homepage": "", | ||
| "license": "", | ||
| "post_processed": null, | ||
| "post_processing_size": null, | ||
| "size_in_bytes": null, | ||
| "splits": null, | ||
| "supervised_keys": null, | ||
| "task_templates": null, | ||
| "version": null | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,14 @@ | ||
| { | ||
| "_data_files": [ | ||
| { | ||
| "filename": "dataset.arrow" | ||
| } | ||
| ], | ||
| "_fingerprint": "48d3ebc4320f1460", | ||
| "_format_columns": null, | ||
| "_format_kwargs": {}, | ||
| "_format_type": null, | ||
| "_indexes": {}, | ||
| "_output_all_columns": false, | ||
| "_split": null | ||
| } |
Binary file not shown.
Binary file not shown.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,50 @@ | ||
| { | ||
| "builder_name": null, | ||
| "citation": "", | ||
| "config_name": null, | ||
| "dataset_size": null, | ||
| "description": "", | ||
| "download_checksums": null, | ||
| "download_size": null, | ||
| "features": { | ||
| "Domain": { | ||
| "dtype": "string", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "Sub domain": { | ||
| "dtype": "string", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "Intent": { | ||
| "dtype": "string", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "value": { | ||
| "dtype": "string", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "labels": { | ||
| "feature": { | ||
| "dtype": "int64", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "length": -1, | ||
| "id": null, | ||
| "_type": "Sequence" | ||
| } | ||
| }, | ||
| "homepage": "", | ||
| "license": "", | ||
| "post_processed": null, | ||
| "post_processing_size": null, | ||
| "size_in_bytes": null, | ||
| "splits": null, | ||
| "supervised_keys": null, | ||
| "task_templates": null, | ||
| "version": null | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,14 @@ | ||
| { | ||
| "_data_files": [ | ||
| { | ||
| "filename": "dataset.arrow" | ||
| } | ||
| ], | ||
| "_fingerprint": "2f19cdd385d5ca9d", | ||
| "_format_columns": null, | ||
| "_format_kwargs": {}, | ||
| "_format_type": null, | ||
| "_indexes": {}, | ||
| "_output_all_columns": false, | ||
| "_split": null | ||
| } |
Binary file added
BIN
+114 KB
clean_data/PoC_10Q_DatasetDict/validation/cache-15e173a85c83c634.arrow
Binary file not shown.
Binary file added
BIN
+114 KB
clean_data/PoC_10Q_DatasetDict/validation/cache-6c870a711d079b3a.arrow
Binary file not shown.
Binary file not shown.
50 changes: 50 additions & 0 deletions
50
clean_data/PoC_10Q_DatasetDict/validation/dataset_info.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,50 @@ | ||
| { | ||
| "builder_name": null, | ||
| "citation": "", | ||
| "config_name": null, | ||
| "dataset_size": null, | ||
| "description": "", | ||
| "download_checksums": null, | ||
| "download_size": null, | ||
| "features": { | ||
| "Domain": { | ||
| "dtype": "string", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "Sub domain": { | ||
| "dtype": "string", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "Intent": { | ||
| "dtype": "string", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "value": { | ||
| "dtype": "string", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "labels": { | ||
| "feature": { | ||
| "dtype": "int64", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "length": -1, | ||
| "id": null, | ||
| "_type": "Sequence" | ||
| } | ||
| }, | ||
| "homepage": "", | ||
| "license": "", | ||
| "post_processed": null, | ||
| "post_processing_size": null, | ||
| "size_in_bytes": null, | ||
| "splits": null, | ||
| "supervised_keys": null, | ||
| "task_templates": null, | ||
| "version": null | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,14 @@ | ||
| { | ||
| "_data_files": [ | ||
| { | ||
| "filename": "dataset.arrow" | ||
| } | ||
| ], | ||
| "_fingerprint": "01297d791d4261c2", | ||
| "_format_columns": null, | ||
| "_format_kwargs": {}, | ||
| "_format_type": null, | ||
| "_indexes": {}, | ||
| "_output_all_columns": false, | ||
| "_split": null | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1 @@ | ||
| {"splits": ["train", "validation", "test"]} |
Binary file not shown.
Binary file not shown.
Binary file not shown.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,60 @@ | ||
| { | ||
| "builder_name": null, | ||
| "citation": "", | ||
| "config_name": null, | ||
| "dataset_size": null, | ||
| "description": "", | ||
| "download_checksums": null, | ||
| "download_size": null, | ||
| "features": { | ||
| "index": { | ||
| "dtype": "int64", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "Domain": { | ||
| "dtype": "string", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "Sub domain": { | ||
| "dtype": "string", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "Intent": { | ||
| "dtype": "string", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "Answer Format": { | ||
| "dtype": "string", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "value": { | ||
| "dtype": "string", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "labels": { | ||
| "feature": { | ||
| "dtype": "int64", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "length": -1, | ||
| "id": null, | ||
| "_type": "Sequence" | ||
| } | ||
| }, | ||
| "homepage": "", | ||
| "license": "", | ||
| "post_processed": null, | ||
| "post_processing_size": null, | ||
| "size_in_bytes": null, | ||
| "splits": null, | ||
| "supervised_keys": null, | ||
| "task_templates": null, | ||
| "version": null | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,14 @@ | ||
| { | ||
| "_data_files": [ | ||
| { | ||
| "filename": "dataset.arrow" | ||
| } | ||
| ], | ||
| "_fingerprint": "c2895b6836830173", | ||
| "_format_columns": null, | ||
| "_format_kwargs": {}, | ||
| "_format_type": null, | ||
| "_indexes": {}, | ||
| "_output_all_columns": false, | ||
| "_split": null | ||
| } |
Binary file not shown.
Binary file not shown.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,60 @@ | ||
| { | ||
| "builder_name": null, | ||
| "citation": "", | ||
| "config_name": null, | ||
| "dataset_size": null, | ||
| "description": "", | ||
| "download_checksums": null, | ||
| "download_size": null, | ||
| "features": { | ||
| "index": { | ||
| "dtype": "int64", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "Domain": { | ||
| "dtype": "string", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "Sub domain": { | ||
| "dtype": "string", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "Intent": { | ||
| "dtype": "string", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "Answer Format": { | ||
| "dtype": "string", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "value": { | ||
| "dtype": "string", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "labels": { | ||
| "feature": { | ||
| "dtype": "int64", | ||
| "id": null, | ||
| "_type": "Value" | ||
| }, | ||
| "length": -1, | ||
| "id": null, | ||
| "_type": "Sequence" | ||
| } | ||
| }, | ||
| "homepage": "", | ||
| "license": "", | ||
| "post_processed": null, | ||
| "post_processing_size": null, | ||
| "size_in_bytes": null, | ||
| "splits": null, | ||
| "supervised_keys": null, | ||
| "task_templates": null, | ||
| "version": null | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,14 @@ | ||
| { | ||
| "_data_files": [ | ||
| { | ||
| "filename": "dataset.arrow" | ||
| } | ||
| ], | ||
| "_fingerprint": "010701e0f50f2307", | ||
| "_format_columns": null, | ||
| "_format_kwargs": {}, | ||
| "_format_type": null, | ||
| "_indexes": {}, | ||
| "_output_all_columns": false, | ||
| "_split": null | ||
| } |
Binary file added
BIN
+2.9 MB
clean_data/phase1_74Q_DatasetDict/validation/cache-101a9cebca124ca8.arrow
Binary file not shown.
Binary file not shown.
Oops, something went wrong.