Spaces:

Hardik-25
/

Sentiment-Analysis

Sleeping

App Files Files Community

Sentiment-Analysis

Commit History

Jul 8

18:48
Update GitHub link to repo URL

Hardik

ccdc581
18:47
Unify critic card top-line and model-type colors to gold

Hardik

ab6ff0e
17:47
Add Featured Screenings section with sample reviews

Hardik

fa77ac9
15:41
Fix seed: run prisma generate before db push

Hardik

21ebebb
15:39
Seed database with model metrics during Docker build

Hardik

faa1abc
15:16
Revert sklearn to 1.5.1, fix multi_class at load time

Hardik

374f547
15:12
Better error logging, direct ML predict endpoint

Hardik

46042a6
15:06
Include prediction errors in response for debugging

Hardik

84a9f0b
14:45
LSTM: fallback to rebuild model arch and load weights

Hardik

d939d85
14:44
LSTM: try keras.saving.load_model first

Hardik

525fd77
14:23
Docker: remove tf-keras, keep native keras 3

Hardik

eafed38
14:22
LSTM: use native keras (Keras 3) for loading, remove tf-keras

Hardik

7772b12
14:19
LSTM: use keras3 directly (not tf-keras) for loading Keras 3 model

Hardik

606b50e
14:15
LSTM: detect file format header, better diagnostics

Hardik

a6150bc
14:14
LSTM: detailed loading diagnostics

Hardik

1e6ceac
14:10
Add /ml-health endpoint for direct ML service access

Hardik

1110c9c
13:57
Forward ML load_errors in health endpoint

Hardik

18daf48
13:56
Add load_errors to health endpoint for debugging

Hardik

b94512a
13:44
Fix LSTM: better loader fallbacks, verify tf-keras

Hardik

b6b2e33
13:38
Fix LSTM loading: try compile=False and multiple backends

Hardik

48320d3
13:28
Fix Dockerfile: separate torch CPU install, add tf-keras

Hardik

f4a3f22
13:16
Fix: resilient predictions, sklearn 1.3.2, LSTM compat, CPU torch

Hardik

1c08948
11:57
Pin sklearn to 1.3.2 for model compatibility

Hardik

a435fdd
11:35
Fix sklearn compatibility for LR model (multi_class attribute)

Hardik

84d0886
11:17
Add Space metadata to README

Hardik

9adee6a
11:17
Initial commit: Sentiment Analysis HF Space

Hardik

3a93fb9

Commit History

Jul 8

Update GitHub link to repo URL

Unify critic card top-line and model-type colors to gold

Add Featured Screenings section with sample reviews

Fix seed: run prisma generate before db push

Seed database with model metrics during Docker build

Revert sklearn to 1.5.1, fix multi_class at load time

Better error logging, direct ML predict endpoint

Include prediction errors in response for debugging

LSTM: fallback to rebuild model arch and load weights

LSTM: try keras.saving.load_model first

Docker: remove tf-keras, keep native keras 3

LSTM: use native keras (Keras 3) for loading, remove tf-keras

LSTM: use keras3 directly (not tf-keras) for loading Keras 3 model

LSTM: detect file format header, better diagnostics

LSTM: detailed loading diagnostics

Add /ml-health endpoint for direct ML service access

Forward ML load_errors in health endpoint

Add load_errors to health endpoint for debugging

Fix LSTM: better loader fallbacks, verify tf-keras

Fix LSTM loading: try compile=False and multiple backends

Fix Dockerfile: separate torch CPU install, add tf-keras

Fix: resilient predictions, sklearn 1.3.2, LSTM compat, CPU torch

Pin sklearn to 1.3.2 for model compatibility

Fix sklearn compatibility for LR model (multi_class attribute)

Add Space metadata to README

Initial commit: Sentiment Analysis HF Space