Upload 46 files
Browse files- .gitattributes +1 -0
- models/nifty_opening_mfe_regressor/outputs/latest_prediction.bak +2 -0
- models/nifty_opening_mfe_regressor/outputs/latest_prediction.csv +1 -1
- models/nifty_opening_mfe_regressor/outputs/summary.json +1 -47
- models/nifty_opening_mfe_regressor/outputs/test_predictions.bak +201 -0
- models/yahoo_history_cache.sqlite3 +2 -2
- nifty_backend/__pycache__/__init__.cpython-311.pyc +0 -0
- nifty_backend/__pycache__/__init__.cpython-312.pyc +0 -0
- nifty_backend/__pycache__/runtime.cpython-311.pyc +3 -0
- nifty_backend/__pycache__/runtime.cpython-312.pyc +3 -0
- nifty_backend/__pycache__/yahoo_history_client.cpython-311.pyc +0 -0
- nifty_backend/runtime.py +1100 -728
.gitattributes
CHANGED
|
@@ -38,3 +38,4 @@ nifty_backend/__pycache__/runtime.cpython-311.pyc filter=lfs diff=lfs merge=lfs
|
|
| 38 |
backend/models/yahoo_history_cache.sqlite3 filter=lfs diff=lfs merge=lfs -text
|
| 39 |
backend/nifty_backend/__pycache__/runtime.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text
|
| 40 |
models/nifty_forecaster/__pycache__/train.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 38 |
backend/models/yahoo_history_cache.sqlite3 filter=lfs diff=lfs merge=lfs -text
|
| 39 |
backend/nifty_backend/__pycache__/runtime.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text
|
| 40 |
models/nifty_forecaster/__pycache__/train.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
nifty_backend/__pycache__/runtime.cpython-312.pyc filter=lfs diff=lfs merge=lfs -text
|
models/nifty_opening_mfe_regressor/outputs/latest_prediction.bak
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
input_date,first5_start,first5_end,first5_close,predicted_up_points,predicted_down_points
|
| 2 |
+
2026-06-11,2026-06-11 09:15:00,2026-06-11 09:19:00,23112.650390625,80.59007717781284,76.48054546871595
|
models/nifty_opening_mfe_regressor/outputs/latest_prediction.csv
CHANGED
|
@@ -1,2 +1,2 @@
|
|
| 1 |
input_date,first5_start,first5_end,first5_close,predicted_up_points,predicted_down_points
|
| 2 |
-
2026-06-
|
|
|
|
| 1 |
input_date,first5_start,first5_end,first5_close,predicted_up_points,predicted_down_points
|
| 2 |
+
2026-06-11,2026-06-11 09:15:00,2026-06-11 09:19:00,23112.650390625,80.59007717781284,76.48054546871592
|
models/nifty_opening_mfe_regressor/outputs/summary.json
CHANGED
|
@@ -1,47 +1 @@
|
|
| 1 |
-
{
|
| 2 |
-
"target_definition": "Predict remaining same-day NIFTY upside/downside points after the first five 1-minute bars.",
|
| 3 |
-
"train_rows": 2221,
|
| 4 |
-
"valid_rows": 405,
|
| 5 |
-
"test_rows": 199,
|
| 6 |
-
"train_start": "2015-01-09",
|
| 7 |
-
"train_end": "2023-12-29",
|
| 8 |
-
"valid_start": "2024-01-01",
|
| 9 |
-
"valid_end": "2025-08-14",
|
| 10 |
-
"test_start": "2025-08-18",
|
| 11 |
-
"test_end": "2026-06-09",
|
| 12 |
-
"feature_count": 188,
|
| 13 |
-
"up": {
|
| 14 |
-
"target": "after5_up_points",
|
| 15 |
-
"selected_model": "random_forest_d6_l10_all+affine_s1.26_b-4",
|
| 16 |
-
"selected_feature_count": 188,
|
| 17 |
-
"validation_mae_points": 62.814071097341994,
|
| 18 |
-
"validation_rmse_points": 95.96458512713473,
|
| 19 |
-
"test_mae_points": 55.869403284612446,
|
| 20 |
-
"test_rmse_points": 79.459874253419,
|
| 21 |
-
"test_high_mfe_mae_points": 120.36235726321215,
|
| 22 |
-
"test_low_mfe_mae_points": 34.22747241931052,
|
| 23 |
-
"baseline_test_mae_points": 75.35728446922032,
|
| 24 |
-
"test_mae_improvement_pct": 25.860646813205825,
|
| 25 |
-
"latest_prediction_points": 63.15162391627527
|
| 26 |
-
},
|
| 27 |
-
"down": {
|
| 28 |
-
"target": "after5_down_points",
|
| 29 |
-
"selected_model": "random_forest_d7_l10_150",
|
| 30 |
-
"selected_feature_count": 150,
|
| 31 |
-
"validation_mae_points": 72.01385673724953,
|
| 32 |
-
"validation_rmse_points": 122.53041341022657,
|
| 33 |
-
"test_mae_points": 62.985231430060715,
|
| 34 |
-
"test_rmse_points": 97.51356947384825,
|
| 35 |
-
"test_high_mfe_mae_points": 141.1492761242954,
|
| 36 |
-
"test_low_mfe_mae_points": 36.75568623065309,
|
| 37 |
-
"baseline_test_mae_points": 77.89575416143268,
|
| 38 |
-
"test_mae_improvement_pct": 19.141637297035604,
|
| 39 |
-
"latest_prediction_points": 71.5788486914341
|
| 40 |
-
},
|
| 41 |
-
"latest_input_date": "2026-06-09",
|
| 42 |
-
"latest_first5_start": "2026-06-09 09:15:00",
|
| 43 |
-
"latest_first5_end": "2026-06-09 09:19:00",
|
| 44 |
-
"latest_first5_close": 23234.849609375,
|
| 45 |
-
"latest_predicted_up_points": 63.15162391627527,
|
| 46 |
-
"latest_predicted_down_points": 71.5788486914341
|
| 47 |
-
}
|
|
|
|
| 1 |
+
{"target_definition": "Predict remaining same-day NIFTY upside/downside points after the first five 1-minute bars.", "train_rows": 2221, "valid_rows": 405, "test_rows": 199, "train_start": "2015-01-09", "train_end": "2023-12-29", "valid_start": "2024-01-01", "valid_end": "2025-08-14", "test_start": "2025-08-18", "test_end": "2026-06-09", "feature_count": 188, "up": {"target": "after5_up_points", "selected_model": "random_forest_d6_l10_all+affine_s1.26_b-4", "selected_feature_count": 188, "validation_mae_points": 62.814071097341994, "validation_rmse_points": 95.96458512713473, "test_mae_points": 55.869403284612446, "test_rmse_points": 79.459874253419, "test_high_mfe_mae_points": 120.36235726321215, "test_low_mfe_mae_points": 34.22747241931052, "baseline_test_mae_points": 75.35728446922032, "test_mae_improvement_pct": 25.860646813205825, "latest_prediction_points": 63.15162391627527}, "down": {"target": "after5_down_points", "selected_model": "random_forest_d7_l10_150", "selected_feature_count": 150, "validation_mae_points": 72.01385673724953, "validation_rmse_points": 122.53041341022657, "test_mae_points": 62.985231430060715, "test_rmse_points": 97.51356947384825, "test_high_mfe_mae_points": 141.1492761242954, "test_low_mfe_mae_points": 36.75568623065309, "baseline_test_mae_points": 77.89575416143268, "test_mae_improvement_pct": 19.141637297035604, "latest_prediction_points": 71.5788486914341}, "latest_first5_start": "2026-06-09 09:15:00", "latest_first5_end": "2026-06-09 09:19:00", "latest_first5_close": 23234.849609375}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
models/nifty_opening_mfe_regressor/outputs/test_predictions.bak
ADDED
|
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
date,first5_close,day_high,day_low,day_close,after5_up_points,after5_down_points,predicted_up_points,predicted_down_points
|
| 2 |
+
2025-08-18,24943.3,25022.0,24852.85,24884.05,78.70000000000073,90.45000000000071,70.74537556748926,69.95608867077122
|
| 3 |
+
2025-08-19,24905.95,25012.65,24873.95,24989.7,106.70000000000071,32.0,69.58622767243469,72.86841515213641
|
| 4 |
+
2025-08-20,24943.7,25088.7,24929.7,25047.15,145.0,14.0,72.2215386978149,66.87535067178419
|
| 5 |
+
2025-08-21,25074.4,25153.65,25054.9,25076.95,79.25,19.5,75.9678756477438,85.01325608135507
|
| 6 |
+
2025-08-22,25022.5,25084.85,24859.15,24869.45,62.34999999999855,163.34999999999854,76.00333285776364,74.38421945646837
|
| 7 |
+
2025-08-25,24923.8,25021.55,24894.35,24978.55,97.75,29.450000000000728,72.08624856357176,72.36965738462226
|
| 8 |
+
2025-08-26,24849.75,24919.65,24689.6,24710.7,69.90000000000146,160.15000000000146,81.82237433198587,75.67181816799939
|
| 9 |
+
2025-08-28,24577.25,24702.65,24481.6,24533.1,125.40000000000146,95.65000000000146,107.37349857848692,103.48101375434892
|
| 10 |
+
2025-08-29,24507.4,24572.45,24404.7,24433.65,65.04999999999927,102.70000000000071,92.69929951194534,127.36320204934307
|
| 11 |
+
2025-09-01,24523.5,24635.6,24432.7,24624.3,112.09999999999854,90.79999999999929,85.59277839975796,102.11100920697749
|
| 12 |
+
2025-09-02,24662.9,24756.1,24522.35,24575.0,93.19999999999708,140.5500000000029,71.68120758636995,76.0402487590437
|
| 13 |
+
2025-09-03,24541.0,24737.05,24533.2,24713.6,196.04999999999927,7.799999999999272,97.43911992220336,85.04967811472694
|
| 14 |
+
2025-09-04,24863.8,24980.75,24708.2,24739.8,116.95000000000071,155.59999999999854,103.12730476704785,78.17111502420333
|
| 15 |
+
2025-09-05,24827.5,24832.35,24621.6,24743.95,4.849999999998545,205.90000000000143,73.98230098745448,85.62699852482866
|
| 16 |
+
2025-09-08,24787.65,24885.5,24751.55,24791.2,97.84999999999854,36.10000000000218,72.29944694258762,65.75039472494996
|
| 17 |
+
2025-09-09,24854.2,24891.8,24814.0,24878.8,37.59999999999855,40.20000000000073,69.44370753005204,77.52099482542334
|
| 18 |
+
2025-09-10,24962.65,25035.7,24915.05,24977.55,73.04999999999927,47.60000000000218,71.89450651813125,72.72213315583208
|
| 19 |
+
2025-09-11,25000.8,25037.3,24940.15,25008.1,36.5,60.64999999999782,70.68275488183907,73.77386846663569
|
| 20 |
+
2025-09-12,25053.3,25139.45,25038.05,25107.7,86.15000000000146,15.25,72.04701987775606,72.71521942996507
|
| 21 |
+
2025-09-15,25091.4,25138.45,25048.75,25069.7,47.04999999999927,42.650000000001455,74.37466301106662,56.21764396713863
|
| 22 |
+
2025-09-16,25106.75,25261.4,25070.45,25254.45,154.65000000000146,36.29999999999927,70.4334423975961,77.09468335603322
|
| 23 |
+
2025-09-17,25297.05,25346.5,25275.35,25330.15,49.45000000000073,21.700000000000728,70.23690402772418,73.54908914096771
|
| 24 |
+
2025-09-18,25411.2,25448.95,25329.75,25420.75,37.75,81.45000000000073,72.10814928193922,68.07462808633801
|
| 25 |
+
2025-09-19,25381.45,25428.75,25286.3,25352.5,47.29999999999927,95.15000000000146,74.70715216901579,89.46626946473036
|
| 26 |
+
2025-09-22,25258.55,25331.7,25151.05,25200.2,73.15000000000146,107.5,71.56191508125039,77.53793666571973
|
| 27 |
+
2025-09-23,25228.05,25261.9,25084.65,25185.8,33.85000000000218,143.39999999999782,69.2148241834104,84.93267760178357
|
| 28 |
+
2025-09-24,25092.3,25149.85,25027.45,25060.9,57.54999999999927,64.84999999999854,73.87437120520443,78.18656010430726
|
| 29 |
+
2025-09-25,25054.4,25092.7,24878.3,24904.55,38.29999999999927,176.10000000000218,71.65598616236045,87.4073952684888
|
| 30 |
+
2025-09-26,24816.0,24868.6,24629.45,24673.1,52.59999999999855,186.54999999999927,75.98342218786617,112.06060895062171
|
| 31 |
+
2025-09-29,24673.7,24791.3,24606.2,24677.55,117.59999999999854,67.5,83.37538480505997,95.65712047233475
|
| 32 |
+
2025-09-30,24713.65,24731.8,24587.7,24633.6,18.149999999997817,125.95000000000071,74.9517147798891,87.6251433757387
|
| 33 |
+
2025-10-01,24620.5,24867.95,24605.95,24853.4,247.4500000000008,14.549999999999272,77.12668758054085,85.91485675791243
|
| 34 |
+
2025-10-03,24785.05,24904.8,24747.55,24895.0,119.75,37.5,81.10550551698013,78.1100418959116
|
| 35 |
+
2025-10-06,24927.05,25095.95,24881.65,25072.55,168.90000000000146,45.39999999999782,69.46213473733515,68.8959058147205
|
| 36 |
+
2025-10-07,25084.9,25220.9,25076.3,25112.8,136.0,8.600000000002183,78.44188298577762,71.62453401261332
|
| 37 |
+
2025-10-08,25146.05,25192.5,25008.5,25023.8,46.45000000000073,137.54999999999927,70.87032840015426,81.93097812216612
|
| 38 |
+
2025-10-09,25058.95,25199.25,25024.3,25170.3,140.29999999999927,34.650000000001455,69.72385100925113,89.36013847299986
|
| 39 |
+
2025-10-10,25221.2,25330.75,25156.85,25278.2,109.54999999999929,64.35000000000218,73.60123392651,77.07921283623484
|
| 40 |
+
2025-10-13,25213.8,25267.3,25152.3,25237.15,53.5,61.5,72.9387780959113,71.96467174317387
|
| 41 |
+
2025-10-14,25293.3,25310.35,25060.55,25123.35,17.049999999999272,232.75,69.75624962391593,75.72942009497733
|
| 42 |
+
2025-10-15,25239.95,25365.15,25159.35,25327.75,125.20000000000071,80.60000000000218,79.00736543634586,89.70179097400522
|
| 43 |
+
2025-10-16,25412.15,25625.4,25376.85,25566.3,213.25,35.30000000000291,69.37806626638448,75.22834036609319
|
| 44 |
+
2025-10-17,25554.05,25781.5,25508.6,25704.7,227.4500000000008,45.45000000000073,70.6399534752275,82.59735724680043
|
| 45 |
+
2025-10-20,25902.8,25926.2,25788.5,25850.7,23.40000000000145,114.29999999999929,82.0103286656743,71.42501744995688
|
| 46 |
+
2025-10-21,25903.25,25934.35,25826.3,25833.3,31.099999999998545,76.95000000000073,70.4734596248554,72.82024209764482
|
| 47 |
+
2025-10-23,26003.75,26104.2,25862.45,25870.3,100.45000000000071,141.29999999999927,78.25616002674558,75.58880300627324
|
| 48 |
+
2025-10-24,25850.8,25944.15,25718.2,25797.45,93.35000000000218,132.59999999999854,85.9352895781675,84.67147328741909
|
| 49 |
+
2025-10-27,25861.4,26005.95,25827.0,25974.0,144.54999999999927,34.400000000001455,49.17301873308348,61.10766648725366
|
| 50 |
+
2025-10-28,25968.1,26041.7,25810.05,25965.4,73.60000000000218,158.04999999999927,72.5812143633312,85.61675283659459
|
| 51 |
+
2025-10-29,25979.75,26097.85,25960.3,26068.3,118.09999999999854,19.450000000000728,75.08031314406708,79.68242908469409
|
| 52 |
+
2025-10-30,25985.15,26032.05,25845.25,25891.2,46.89999999999782,139.90000000000146,73.39380876964638,74.325383761321
|
| 53 |
+
2025-10-31,25862.85,25953.75,25711.2,25732.55,90.90000000000146,151.64999999999782,73.94864338763755,79.1021674617272
|
| 54 |
+
2025-11-03,25687.85,25803.1,25645.5,25774.3,115.25,42.34999999999855,48.84044727691018,67.28257199135699
|
| 55 |
+
2025-11-04,25755.4,25787.4,25578.4,25586.25,32.0,177.0,71.3743139533095,89.3481792230919
|
| 56 |
+
2025-11-06,25666.7,25679.15,25491.55,25519.95,12.450000000000728,175.15000000000146,77.85466759246198,90.57445591555329
|
| 57 |
+
2025-11-07,25378.15,25551.25,25318.45,25510.05,173.09999999999854,59.70000000000073,82.87633192312792,90.85600003629604
|
| 58 |
+
2025-11-10,25554.6,25653.45,25503.5,25574.25,98.85000000000218,51.09999999999855,76.07720514892765,92.5203310121857
|
| 59 |
+
2025-11-11,25544.8,25715.8,25449.25,25705.55,171.0,95.54999999999929,84.99031835536154,91.46776795888675
|
| 60 |
+
2025-11-12,25807.2,25934.55,25781.15,25874.0,127.34999999999854,26.049999999999272,72.59276739431719,69.43894779255301
|
| 61 |
+
2025-11-13,25843.95,26010.7,25808.4,25884.1,166.75,35.54999999999927,78.67378928776296,67.05446226149067
|
| 62 |
+
2025-11-14,25810.7,25940.2,25740.8,25916.8,129.5,69.90000000000146,73.19872933440267,87.55904589996446
|
| 63 |
+
2025-11-17,25951.05,26024.2,25906.35,26014.3,73.15000000000146,44.70000000000073,69.76315356672858,97.59555559580076
|
| 64 |
+
2025-11-18,25947.35,26029.85,25876.5,25894.7,82.5,70.84999999999854,85.51147346645418,80.55471837004212
|
| 65 |
+
2025-11-19,25857.5,26074.65,25856.2,26052.7,217.15000000000143,1.2999999999992724,80.68382090556915,94.6026325119518
|
| 66 |
+
2025-11-20,26099.7,26246.65,26063.2,26197.4,146.95000000000073,36.5,70.58602673534355,77.26577489877992
|
| 67 |
+
2025-11-21,26138.75,26179.2,26052.2,26063.95,40.45000000000073,86.54999999999927,72.78494759917074,88.50537506994732
|
| 68 |
+
2025-11-24,26097.25,26142.8,25912.15,25943.35,45.54999999999927,185.0999999999985,71.59439136628663,98.01259127172162
|
| 69 |
+
2025-11-25,25965.0,26032.6,25857.5,25860.3,67.59999999999854,107.5,74.81866080624437,97.64266493121366
|
| 70 |
+
2025-11-26,25969.7,26215.15,25842.95,26203.5,245.4500000000008,126.75,90.3814582306311,86.97774096205734
|
| 71 |
+
2025-11-27,26251.95,26310.45,26141.9,26219.85,58.5,110.04999999999929,71.40800619164884,75.89199618666595
|
| 72 |
+
2025-11-28,26242.15,26280.75,26172.4,26204.55,38.59999999999855,69.75,72.7899189230503,68.94343157609912
|
| 73 |
+
2025-12-01,26285.3,26325.8,26124.2,26175.95,40.5,161.09999999999854,70.47431107358459,75.68478873086691
|
| 74 |
+
2025-12-02,26141.5,26154.6,25997.85,26057.0,13.099999999998545,143.65000000000146,74.4344525604593,86.98101762857138
|
| 75 |
+
2025-12-03,26031.25,26066.45,25891.0,25985.1,35.20000000000073,140.25,70.95415206130762,80.43735765423229
|
| 76 |
+
2025-12-04,25949.55,26098.25,25938.95,26017.1,148.70000000000073,10.599999999998545,70.73708673203622,80.01080718413094
|
| 77 |
+
2025-12-05,26051.05,26202.6,25985.35,26176.65,151.54999999999927,65.70000000000073,72.41683194442193,96.03195181892916
|
| 78 |
+
2025-12-08,26159.7,26178.7,25892.25,25932.8,19.0,267.4500000000007,69.67299117722322,81.02444831648698
|
| 79 |
+
2025-12-09,25819.8,25923.65,25728.0,25841.75,103.85000000000218,91.79999999999929,77.47469251817466,95.02942758445396
|
| 80 |
+
2025-12-10,25880.55,25947.65,25734.55,25742.65,67.10000000000218,146.0,71.70553491482723,98.1837081927547
|
| 81 |
+
2025-12-11,25757.1,25922.8,25693.25,25898.4,165.70000000000073,63.84999999999855,76.56354511911341,101.94574105996686
|
| 82 |
+
2025-12-12,26002.55,26057.6,25938.45,26043.0,55.04999999999927,64.09999999999854,69.67619298888475,79.50154765698446
|
| 83 |
+
2025-12-15,25953.3,26047.15,25904.75,26014.0,93.85000000000218,48.54999999999927,75.17828185471886,76.85009428534134
|
| 84 |
+
2025-12-16,25943.3,25980.75,25834.35,25851.35,37.45000000000073,108.95000000000071,71.27112421993293,81.85242825234664
|
| 85 |
+
2025-12-17,25872.6,25929.15,25770.35,25821.8,56.55000000000291,102.25,72.35835339450391,87.43541006469988
|
| 86 |
+
2025-12-18,25777.75,25902.35,25726.3,25815.65,124.59999999999854,51.45000000000073,74.43183502860306,85.33298803694375
|
| 87 |
+
2025-12-19,25925.1,25993.35,25880.45,25961.4,68.25,44.64999999999782,70.77069567565373,83.78604666129061
|
| 88 |
+
2025-12-22,26093.9,26180.7,26047.8,26162.75,86.79999999999927,46.10000000000218,70.42228403925822,72.76339644091539
|
| 89 |
+
2025-12-23,26166.7,26233.55,26119.05,26165.95,66.84999999999854,47.650000000001455,74.84971589574519,69.426936900949
|
| 90 |
+
2025-12-24,26198.25,26236.4,26123.0,26141.65,38.150000000001455,75.25,71.48754603427759,73.72186108153664
|
| 91 |
+
2025-12-26,26131.05,26144.2,26008.6,26047.65,13.150000000001455,122.45000000000071,45.48128688932305,57.062560579537895
|
| 92 |
+
2025-12-29,26050.5,26106.8,25920.3,25949.8,56.29999999999927,130.20000000000073,75.70015606822022,78.00564702749449
|
| 93 |
+
2025-12-30,25908.05,25976.75,25878.0,25970.55,68.70000000000073,30.049999999999272,75.2522086126314,77.13518357533343
|
| 94 |
+
2025-12-31,26013.65,26187.95,25969.0,26141.85,174.29999999999927,44.650000000001455,73.24189431613242,73.79354269787787
|
| 95 |
+
2026-01-01,26167.8,26197.55,26113.4,26140.25,29.75,54.39999999999782,71.71010503029348,73.54519160205173
|
| 96 |
+
2026-01-02,26181.65,26340.0,26118.4,26335.7,158.34999999999854,63.25,45.480429907888656,57.12647950293099
|
| 97 |
+
2026-01-05,26340.25,26373.2,26210.05,26244.65,32.95000000000073,130.20000000000073,70.46179801639443,81.45276466292157
|
| 98 |
+
2026-01-06,26195.8,26273.95,26124.75,26174.65,78.15000000000146,71.04999999999927,79.36914045104106,92.38591642666192
|
| 99 |
+
2026-01-07,26125.65,26187.15,26067.9,26142.9,61.5,57.75,72.55581417361594,83.15694141096833
|
| 100 |
+
2026-01-08,26123.25,26133.2,25858.45,25868.9,9.950000000000728,264.7999999999993,71.04783101366327,82.46291134118252
|
| 101 |
+
2026-01-09,25938.8,25940.6,25623.0,25703.7,1.7999999999992724,315.7999999999993,86.53974081668476,121.44759821661056
|
| 102 |
+
2026-01-12,25611.95,25813.15,25473.4,25806.1,201.2000000000008,138.54999999999927,83.95949739270267,120.28936873981168
|
| 103 |
+
2026-01-13,25846.25,25899.8,25603.3,25714.2,53.54999999999927,242.9500000000008,78.19680117941645,84.9829292741713
|
| 104 |
+
2026-01-14,25683.25,25791.75,25603.95,25669.1,108.5,79.29999999999927,82.35604656222411,99.82529425771892
|
| 105 |
+
2026-01-16,25730.45,25873.5,25662.4,25701.9,143.04999999999927,68.04999999999927,72.2288158291699,96.07795888190776
|
| 106 |
+
2026-01-19,25597.4,25653.3,25494.35,25555.5,55.89999999999782,103.05000000000292,93.52077464705306,93.8292063036645
|
| 107 |
+
2026-01-20,25558.25,25585.0,25171.35,25225.35,26.75,386.9000000000015,76.71942144430174,79.78554817218038
|
| 108 |
+
2026-01-21,25242.4,25300.95,24919.8,25168.1,58.54999999999927,322.6000000000022,130.94997110273525,147.75173361890398
|
| 109 |
+
2026-01-22,25318.0,25435.75,25168.5,25320.45,117.75,149.5,85.07263391734676,130.19406357107007
|
| 110 |
+
2026-01-23,25275.3,25347.95,25025.3,25064.75,72.65000000000146,250.0,86.95616205286174,98.93004959582946
|
| 111 |
+
2026-01-27,25009.95,25246.65,24932.55,25234.1,236.7000000000008,77.40000000000146,110.68260525851476,129.7114495843547
|
| 112 |
+
2026-01-28,25336.3,25372.1,25187.65,25348.05,35.79999999999927,148.64999999999782,89.71179240489799,109.83708610878163
|
| 113 |
+
2026-01-29,25280.55,25458.15,25159.8,25422.1,177.60000000000218,120.75,91.59350021026472,87.43822382386271
|
| 114 |
+
2026-01-30,25259.3,25370.7,25213.65,25315.8,111.40000000000146,45.64999999999782,79.05064818970524,100.1312421862931
|
| 115 |
+
2026-02-01,25282.8,25440.9,24571.75,24768.0,158.10000000000218,711.0499999999993,80.05582527903351,87.1593675112166
|
| 116 |
+
2026-02-02,24806.35,25108.1,24679.4,25079.9,301.75,126.94999999999708,86.6858901745076,81.9244305205442
|
| 117 |
+
2026-02-03,25809.75,26341.2,25641.3,25714.8,531.4500000000007,168.45000000000073,209.3466476279516,140.6950158750343
|
| 118 |
+
2026-02-04,25710.7,25818.55,25563.95,25737.5,107.84999999999854,146.75,123.34674640202677,112.15100241628755
|
| 119 |
+
2026-02-05,25727.35,25757.65,25579.5,25641.6,30.30000000000291,147.84999999999854,78.92667069768866,93.48294833342888
|
| 120 |
+
2026-02-06,25603.5,25703.95,25491.9,25673.6,100.45000000000071,111.59999999999854,81.63730431628646,108.84971109953882
|
| 121 |
+
2026-02-09,25815.55,25922.25,25780.9,25863.3,106.70000000000071,34.64999999999782,97.04614278500875,83.38428889831818
|
| 122 |
+
2026-02-10,25918.05,25989.45,25870.45,25916.8,71.40000000000146,47.59999999999855,72.55379470719815,80.47042331164333
|
| 123 |
+
2026-02-11,25985.0,26009.4,25899.8,25945.35,24.40000000000145,85.20000000000073,70.82761961162062,78.822407881009
|
| 124 |
+
2026-02-12,25855.25,25906.7,25752.4,25796.15,51.45000000000073,102.84999999999854,74.42962687752149,69.6320381757916
|
| 125 |
+
2026-02-13,25596.4,25630.35,25444.3,25460.55,33.94999999999709,152.10000000000218,78.73111917226437,92.65335041306253
|
| 126 |
+
2026-02-16,25472.2,25697.0,25372.7,25682.45,224.79999999999927,99.5,87.51077339277226,135.77441133340997
|
| 127 |
+
2026-02-17,25612.45,25764.4,25570.3,25716.0,151.95000000000073,42.150000000001455,74.20532764340571,70.59556735334088
|
| 128 |
+
2026-02-18,25742.05,25828.05,25645.15,25805.7,86.0,96.89999999999782,69.60174388514015,87.14731231617911
|
| 129 |
+
2026-02-19,25853.9,25885.3,25388.75,25416.45,31.399999999997817,465.1500000000015,72.82233481769892,77.47993082146262
|
| 130 |
+
2026-02-20,25452.9,25663.55,25379.75,25565.9,210.64999999999785,73.15000000000146,101.23325383545428,120.39677579437908
|
| 131 |
+
2026-02-23,25698.35,25771.45,25609.35,25704.0,73.10000000000218,89.0,78.13994225569839,102.6805412273098
|
| 132 |
+
2026-02-24,25570.55,25641.8,25327.6,25460.25,71.25,242.9500000000008,84.66998953575761,78.35520991871599
|
| 133 |
+
2026-02-25,25561.8,25652.6,25428.2,25478.65,90.79999999999929,133.59999999999854,78.48076576983638,96.14961930214676
|
| 134 |
+
2026-02-26,25535.1,25572.95,25400.95,25493.3,37.85000000000218,134.14999999999782,73.42761359209224,92.16432309346206
|
| 135 |
+
2026-02-27,25395.4,25476.4,25141.3,25181.8,81.0,254.10000000000213,84.86928109002694,89.3313420570492
|
| 136 |
+
2026-03-02,24892.95,24989.35,24603.5,24849.75,96.39999999999782,289.4500000000007,111.27759797579716,107.15701801512222
|
| 137 |
+
2026-03-04,24385.1,24602.45,24305.4,24473.95,217.35000000000213,79.69999999999709,133.72126269580576,155.30789682765342
|
| 138 |
+
2026-03-05,24584.85,24854.2,24529.4,24737.45,269.3500000000022,55.44999999999709,162.08234784984276,162.40605803165704
|
| 139 |
+
2026-03-06,24594.4,24700.9,24415.75,24469.4,106.5,178.65000000000146,117.98380433944612,116.83602544783804
|
| 140 |
+
2026-03-09,23774.35,24078.15,23697.8,24005.8,303.8000000000029,76.54999999999927,192.3591586795632,146.88020524223515
|
| 141 |
+
2026-03-10,24149.0,24303.8,24079.95,24286.15,154.79999999999927,69.04999999999927,192.7937738097792,158.9186209194774
|
| 142 |
+
2026-03-11,24285.9,24299.0,23834.3,23848.2,13.099999999998545,451.6000000000022,133.54653076939334,121.19414544015564
|
| 143 |
+
2026-03-12,23563.15,23833.15,23556.3,23639.35,270.0,6.850000000002183,192.6358883055884,120.53074403063889
|
| 144 |
+
2026-03-13,23450.25,23492.4,23112.0,23170.9,42.150000000001455,338.25,145.7091162926563,146.68104013479658
|
| 145 |
+
2026-03-16,23172.55,23502.0,22955.25,23355.6,329.4500000000007,217.29999999999927,170.38500881814582,207.8442210393264
|
| 146 |
+
2026-03-17,23395.55,23656.8,23346.6,23558.8,261.25,48.95000000000073,156.7943098659703,149.21233378254283
|
| 147 |
+
2026-03-18,23721.9,23862.25,23618.45,23764.1,140.34999999999854,103.45000000000071,121.95109115304878,116.42727703008954
|
| 148 |
+
2026-03-19,23289.5,23378.7,22930.35,23087.85,89.20000000000073,359.15000000000146,133.90428933906327,137.31867907141643
|
| 149 |
+
2026-03-20,23281.5,23345.15,23067.6,23134.65,63.650000000001455,213.90000000000143,159.7676630786322,165.0265464253639
|
| 150 |
+
2026-03-23,22687.45,22851.7,22471.25,22492.65,164.25,216.2000000000008,145.85353407241462,152.4341252582677
|
| 151 |
+
2026-03-24,22785.15,23057.3,22624.2,22958.4,272.1499999999978,160.95000000000073,207.01095264874107,154.6488830452536
|
| 152 |
+
2026-03-25,23162.6,23465.35,23063.2,23309.0,302.75,99.39999999999782,132.30015580160267,124.7102392167061
|
| 153 |
+
2026-03-27,23041.8,23186.1,22804.55,22839.5,144.29999999999927,237.25,138.49642324859562,132.77812683059364
|
| 154 |
+
2026-03-30,22522.45,22714.1,22283.85,22379.2,191.64999999999785,238.60000000000213,137.43517166951938,113.26298404384518
|
| 155 |
+
2026-04-01,22887.0,22941.3,22618.6,22703.15,54.29999999999927,268.40000000000146,171.94720651853035,142.51587723198915
|
| 156 |
+
2026-04-02,22228.0,22782.3,22182.55,22700.7,554.2999999999993,45.45000000000073,157.50885517232763,135.03847736028655
|
| 157 |
+
2026-04-06,22666.05,22998.35,22542.95,22959.45,332.2999999999993,123.09999999999854,144.97157821899438,110.86736478379764
|
| 158 |
+
2026-04-07,22773.05,23153.85,22719.3,23129.95,380.7999999999993,53.75,111.3757230804756,120.98351003129396
|
| 159 |
+
2026-04-08,23899.95,23961.25,23837.65,23892.75,61.29999999999927,62.29999999999927,102.2801592496814,103.1134383545202
|
| 160 |
+
2026-04-09,23935.650390625,23989.75,23683.349609375,23766.05078125,54.099609375,252.30078125,97.56128839578804,120.80458797190984
|
| 161 |
+
2026-04-10,23965.69921875,24073.80078125,23867.19921875,24051.80078125,108.1015625,98.5,85.23780890426106,116.17509968142504
|
| 162 |
+
2026-04-13,23578.55078125,23905.650390625,23556.150390625,23818.900390625,327.099609375,22.400390625,101.5126595166479,98.57767387007569
|
| 163 |
+
2026-04-15,24230.849609375,24273.150390625,24146.69921875,24211.900390625,42.30078125,84.150390625,87.99325993978478,100.5389864062017
|
| 164 |
+
2026-04-16,24390.55078125,24400.099609375,24103.099609375,24188.400390625,9.548828125,287.451171875,75.10031206149125,96.78284688386456
|
| 165 |
+
2026-04-17,24207.55078125,24370.25,24109.44921875,24366.900390625,162.69921875,98.1015625,93.875672724558,113.6195855929118
|
| 166 |
+
2026-04-20,24373.099609375,24394.05078125,24318.0,24330.900390625,20.951171875,55.099609375,74.03118715657969,70.17966380671794
|
| 167 |
+
2026-04-21,24468.849609375,24600.849609375,24357.150390625,24581.05078125,132.0,111.69921875,86.20844571936449,102.2667119048698
|
| 168 |
+
2026-04-22,24479.30078125,24515.75,24353.69921875,24367.650390625,36.44921875,125.6015625,78.71803618671171,105.18692808784276
|
| 169 |
+
2026-04-23,24201.349609375,24309.900390625,24138.849609375,24156.05078125,108.55078125,62.5,84.05594012758098,99.00734685037855
|
| 170 |
+
2026-04-24,24124.19921875,24203.349609375,23815.349609375,23903.94921875,79.150390625,308.849609375,90.14180250621698,136.87579336691633
|
| 171 |
+
2026-04-27,24020.349609375,24130.30078125,23952.0,24110.19921875,109.951171875,68.349609375,99.59614157374158,118.31424726361335
|
| 172 |
+
2026-04-28,24093.849609375,24181.75,23958.05078125,24016.5,87.900390625,135.798828125,88.15968826749,106.64812371296172
|
| 173 |
+
2026-04-29,24090.80078125,24334.19921875,24060.650390625,24163.599609375,243.3984375,30.150390625,87.90088049432329,124.95795081910784
|
| 174 |
+
2026-04-30,23945.25,24086.94921875,23797.05078125,23997.55078125,141.69921875,148.19921875,139.48308205556245,111.61338896287434
|
| 175 |
+
2026-05-04,24177.05078125,24289.19921875,24005.30078125,24119.30078125,112.1484375,171.75,147.62463980491148,110.82979739572832
|
| 176 |
+
2026-05-05,24064.19921875,24080.94921875,23883.5,24032.80078125,16.75,180.69921875,104.19136737845044,118.00286130314204
|
| 177 |
+
2026-05-06,24175.80078125,24355.55078125,23999.0,24330.94921875,179.75,176.80078125,89.34877716071158,100.09239323156596
|
| 178 |
+
2026-05-07,24318.25,24481.94921875,24284.650390625,24326.650390625,163.69921875,33.599609375,144.18742265088838,101.03766931638432
|
| 179 |
+
2026-05-08,24219.30078125,24253.44921875,24127.69921875,24176.150390625,34.1484375,91.6015625,113.44501924079982,105.61263750990524
|
| 180 |
+
2026-05-11,23918.75,23997.0,23801.25,23820.349609375,78.25,117.5,115.09320335959804,89.86773115957116
|
| 181 |
+
2026-05-12,23736.900390625,23754.150390625,23349.099609375,23430.55078125,17.25,387.80078125,116.96920740241298,142.73344731125428
|
| 182 |
+
2026-05-13,23405.400390625,23582.80078125,23263.05078125,23428.69921875,177.400390625,142.349609375,175.97531700031948,150.41964833343525
|
| 183 |
+
2026-05-14,23550.05078125,23776.650390625,23426.849609375,23713.75,226.599609375,123.201171875,172.47993492418186,120.64942388533476
|
| 184 |
+
2026-05-15,23718.900390625,23838.94921875,23610.80078125,23643.5,120.048828125,108.099609375,116.92088358715652,117.22659612227842
|
| 185 |
+
2026-05-18,23400.5,23695.400390625,23317.55078125,23644.44921875,294.900390625,82.94921875,122.25057682854032,99.44379095807834
|
| 186 |
+
2026-05-19,23735.099609375,23782.19921875,23587.25,23606.150390625,47.099609375,147.849609375,89.25678651875887,118.2088244294284
|
| 187 |
+
2026-05-20,23460.650390625,23690.75,23403.75,23664.349609375,230.099609375,56.900390625,90.6801349163642,107.62981114189007
|
| 188 |
+
2026-05-21,23766.849609375,23859.150390625,23596.849609375,23654.69921875,92.30078125,170.0,143.97390699531186,119.33033220862224
|
| 189 |
+
2026-05-22,23693.5,23835.599609375,23675.349609375,23748.849609375,142.099609375,18.150390625,110.3358336575918,101.93356091893207
|
| 190 |
+
2026-05-25,23967.599609375,24054.400390625,23924.400390625,24049.900390625,86.80078125,43.19921875,94.48529797429144,78.70386364984326
|
| 191 |
+
2026-05-26,24012.55078125,24089.55078125,23885.44921875,23933.75,77.0,127.1015625,79.73076033164853,83.18524021655392
|
| 192 |
+
2026-05-27,23926.349609375,23983.0,23858.55078125,23907.150390625,56.650390625,67.798828125,82.86160430091547,111.90618562168372
|
| 193 |
+
2026-05-29,23963.30078125,23998.69921875,23486.599609375,23547.75,35.3984375,476.701171875,103.19623464475224,101.30160095874687
|
| 194 |
+
2026-06-01,23633.0,23727.650390625,23358.150390625,23379.19921875,94.650390625,274.849609375,147.97873066706777,108.07717150797622
|
| 195 |
+
2026-06-02,23283.19921875,23556.599609375,23229.150390625,23520.69921875,273.400390625,54.048828125,104.11710291744272,127.52289995410068
|
| 196 |
+
2026-06-03,23299.30078125,23459.349609375,23152.150390625,23396.94921875,160.048828125,147.150390625,119.81095584527132,121.31295450722716
|
| 197 |
+
2026-06-04,23345.900390625,23465.150390625,23249.599609375,23416.55078125,119.25,96.30078125,96.4568581173244,123.15485148279662
|
| 198 |
+
2026-06-05,23456.150390625,23513.650390625,23282.80078125,23366.69921875,57.5,173.349609375,113.41119571155151,102.86641440643322
|
| 199 |
+
2026-06-08,23130.55078125,23266.849609375,23071.5,23123.0,136.298828125,59.05078125,71.99673733444993,66.32122469457533
|
| 200 |
+
2026-06-09,23234.849609375,,,,,,80.52086115732924,74.45651902291536
|
| 201 |
+
2026-06-11,23112.650390625,,,,,,80.59007717781284,76.48054546871595
|
models/yahoo_history_cache.sqlite3
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75c3f55a2adee670c10dbadd1c998d3ce773ed067c8e196ed2c7539ca6f8eb87
|
| 3 |
+
size 397312
|
nifty_backend/__pycache__/__init__.cpython-311.pyc
ADDED
|
Binary file (257 Bytes). View file
|
|
|
nifty_backend/__pycache__/__init__.cpython-312.pyc
ADDED
|
Binary file (246 Bytes). View file
|
|
|
nifty_backend/__pycache__/runtime.cpython-311.pyc
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eac2a9d465d264f6ebb982a4f2b7fbd61ef4db81c5a3549543b07cb103b8d680
|
| 3 |
+
size 138158
|
nifty_backend/__pycache__/runtime.cpython-312.pyc
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:577bb7a5580d51f89125710300b1fb2c2da89613a7053c0c689494052442b6ef
|
| 3 |
+
size 107926
|
nifty_backend/__pycache__/yahoo_history_client.cpython-311.pyc
ADDED
|
Binary file (27.8 kB). View file
|
|
|
nifty_backend/runtime.py
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
from __future__ import annotations
|
| 2 |
|
| 3 |
-
import json
|
| 4 |
-
import copy
|
| 5 |
-
import os
|
| 6 |
-
import sys
|
| 7 |
-
import threading
|
| 8 |
from dataclasses import dataclass
|
| 9 |
from datetime import date, datetime, time, timedelta
|
| 10 |
from functools import lru_cache
|
|
@@ -12,10 +12,10 @@ from pathlib import Path
|
|
| 12 |
from typing import Any
|
| 13 |
from zoneinfo import ZoneInfo
|
| 14 |
|
| 15 |
-
import joblib
|
| 16 |
-
import numpy as np
|
| 17 |
-
import pandas as pd
|
| 18 |
-
from nifty_backend.yahoo_history_client import YahooHistoryClient
|
| 19 |
|
| 20 |
try:
|
| 21 |
import pandas_market_calendars as mcal
|
|
@@ -24,16 +24,16 @@ except ImportError: # pragma: no cover - production dependency, local fallback
|
|
| 24 |
|
| 25 |
|
| 26 |
IST = ZoneInfo("Asia/Kolkata")
|
| 27 |
-
YAHOO_NIFTY_SYMBOL = "^NSEI"
|
| 28 |
-
MARKET_CLOSE = time(15, 30)
|
| 29 |
-
FIRST5_READY = time(9, 20)
|
| 30 |
-
CLOSE_REFRESH_READY = time(15, 45)
|
| 31 |
-
TPLUS1_READY = time(14, 30)
|
| 32 |
-
STALE_CHECK_INTERVAL_SECONDS = 5
|
| 33 |
-
BACKEND_ROOT = Path(__file__).resolve().parents[1]
|
| 34 |
-
DATA_DIR = BACKEND_ROOT / "data"
|
| 35 |
-
MODEL_DIR = BACKEND_ROOT / "models"
|
| 36 |
-
YAHOO_CACHE_PATH = MODEL_DIR / "yahoo_history_cache.sqlite3"
|
| 37 |
OPENING_DATASET_PATH = DATA_DIR / "opening_direction_training_dataset.parquet"
|
| 38 |
NIFTY_1M_PATH = DATA_DIR / "nifty50_1m.parquet"
|
| 39 |
NIFTY_1D_PATH = DATA_DIR / "nifty50_1d.parquet"
|
|
@@ -43,21 +43,29 @@ TEST_PREDICTIONS_PATH = DATA_DIR / "test_predictions.parquet"
|
|
| 43 |
TOMORROW_MODEL_PATH = MODEL_DIR / "nifty_tomorrow_direction_model.joblib"
|
| 44 |
TOMORROW_LATEST_PATH = MODEL_DIR / "tomorrow_latest_prediction.csv"
|
| 45 |
TOMORROW_SUMMARY_PATH = MODEL_DIR / "tomorrow_summary.json"
|
| 46 |
-
TOMORROW_TEST_PREDICTIONS_PATH = DATA_DIR / "tomorrow_test_predictions.parquet"
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
)
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
TPLUS1_LATEST_PATH = MODEL_DIR / "tplus1_latest_prediction.csv"
|
| 59 |
TPLUS1_SUMMARY_PATH = MODEL_DIR / "tplus1_summary.json"
|
| 60 |
TPLUS1_TEST_PREDICTIONS_PATH = DATA_DIR / "tplus1_test_predictions.parquet"
|
|
|
|
|
|
|
| 61 |
REFRESH_STATE_PATH = MODEL_DIR / "refresh_state.json"
|
| 62 |
REFRESH_WAITING = "waiting_second_payload"
|
| 63 |
REFRESH_REFRESHING = "refreshing"
|
|
@@ -81,8 +89,8 @@ DECISION_OVERLAYS = [
|
|
| 81 |
},
|
| 82 |
]
|
| 83 |
|
| 84 |
-
_dashboard_payload_lock = threading.Lock()
|
| 85 |
-
_stale_refresh_lock = threading.Lock()
|
| 86 |
|
| 87 |
|
| 88 |
def utc_now_iso() -> str:
|
|
@@ -179,6 +187,31 @@ def previous_trading_day(start: date) -> date:
|
|
| 179 |
return pd.Timestamp(schedule.index[-1]).date()
|
| 180 |
|
| 181 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 182 |
class ProbabilityBlend:
|
| 183 |
def __init__(self, models: list[Any], weights: np.ndarray):
|
| 184 |
self.models = models
|
|
@@ -278,7 +311,7 @@ def read_training_dataset() -> pd.DataFrame:
|
|
| 278 |
return df.sort_values("date").reset_index(drop=True)
|
| 279 |
|
| 280 |
|
| 281 |
-
def normalize_yahoo_frame(df: pd.DataFrame) -> pd.DataFrame:
|
| 282 |
if df.empty:
|
| 283 |
return pd.DataFrame(columns=["date", "open", "high", "low", "close", "volume"])
|
| 284 |
if isinstance(df.columns, pd.MultiIndex):
|
|
@@ -304,81 +337,81 @@ def normalize_yahoo_frame(df: pd.DataFrame) -> pd.DataFrame:
|
|
| 304 |
for src, dst in rename.items():
|
| 305 |
if src in df.columns and dst not in out.columns:
|
| 306 |
out[dst] = pd.to_numeric(df[src], errors="coerce")
|
| 307 |
-
return out.dropna(subset=["date", "open", "high", "low", "close"]).sort_values("date")
|
| 308 |
-
|
| 309 |
-
|
| 310 |
-
@lru_cache(maxsize=1)
|
| 311 |
-
def yahoo_history_client() -> YahooHistoryClient:
|
| 312 |
-
return YahooHistoryClient(cache_path=YAHOO_CACHE_PATH)
|
| 313 |
-
|
| 314 |
-
|
| 315 |
-
def period_start(period: str, *, end: datetime) -> datetime:
|
| 316 |
-
text = str(period).strip().lower()
|
| 317 |
-
units = {
|
| 318 |
-
"d": "days",
|
| 319 |
-
"wk": "weeks",
|
| 320 |
-
"mo": "months",
|
| 321 |
-
"y": "years",
|
| 322 |
-
}
|
| 323 |
-
for suffix, unit in units.items():
|
| 324 |
-
if text.endswith(suffix):
|
| 325 |
-
raw_value = text[: -len(suffix)]
|
| 326 |
-
if not raw_value.isdigit():
|
| 327 |
-
break
|
| 328 |
-
value = int(raw_value)
|
| 329 |
-
if unit == "days":
|
| 330 |
-
return end - timedelta(days=value)
|
| 331 |
-
if unit == "weeks":
|
| 332 |
-
return end - timedelta(weeks=value)
|
| 333 |
-
if unit == "months":
|
| 334 |
-
return end - timedelta(days=value * 31)
|
| 335 |
-
if unit == "years":
|
| 336 |
-
return end - timedelta(days=value * 366)
|
| 337 |
-
raise ValueError(f"Unsupported Yahoo period: {period!r}")
|
| 338 |
-
|
| 339 |
-
|
| 340 |
-
def yahoo_history_to_ohlcv(frame: pd.DataFrame, *, daily: bool) -> pd.DataFrame:
|
| 341 |
-
if frame.empty:
|
| 342 |
-
return pd.DataFrame(columns=["date", "open", "high", "low", "close", "volume"])
|
| 343 |
-
out = frame.rename(columns={"timestamp": "date"}).copy()
|
| 344 |
-
out["date"] = pd.to_datetime(out["date"], errors="coerce")
|
| 345 |
-
if daily:
|
| 346 |
-
out["date"] = out["date"].dt.normalize()
|
| 347 |
-
for column in ("open", "high", "low", "close", "volume"):
|
| 348 |
-
out[column] = pd.to_numeric(out[column], errors="coerce")
|
| 349 |
-
return (
|
| 350 |
-
out[["date", "open", "high", "low", "close", "volume"]]
|
| 351 |
-
.dropna(subset=["date", "open", "high", "low", "close"])
|
| 352 |
-
.drop_duplicates("date", keep="last")
|
| 353 |
-
.sort_values("date")
|
| 354 |
-
.reset_index(drop=True)
|
| 355 |
-
)
|
| 356 |
-
|
| 357 |
-
|
| 358 |
-
def fetch_yahoo_minutes(period: str = "5d") -> pd.DataFrame:
|
| 359 |
-
end = datetime.now(IST).replace(tzinfo=None) + timedelta(minutes=5)
|
| 360 |
-
start = period_start(period, end=end)
|
| 361 |
-
raw = yahoo_history_client().fetch_history(
|
| 362 |
-
YAHOO_NIFTY_SYMBOL,
|
| 363 |
-
interval="1m",
|
| 364 |
-
start=start,
|
| 365 |
-
end=end,
|
| 366 |
-
include_prepost=False,
|
| 367 |
-
)
|
| 368 |
-
return yahoo_history_to_ohlcv(raw, daily=False)
|
| 369 |
-
|
| 370 |
-
|
| 371 |
-
def fetch_yahoo_daily(period: str = "1mo") -> pd.DataFrame:
|
| 372 |
-
end = datetime.now(IST).replace(tzinfo=None) + timedelta(days=1)
|
| 373 |
-
start = period_start(period, end=end)
|
| 374 |
-
raw = yahoo_history_client().fetch_history(
|
| 375 |
-
YAHOO_NIFTY_SYMBOL,
|
| 376 |
-
interval="1d",
|
| 377 |
-
start=start,
|
| 378 |
-
end=end,
|
| 379 |
-
include_prepost=False,
|
| 380 |
-
)
|
| 381 |
-
return yahoo_history_to_ohlcv(raw, daily=True)
|
| 382 |
|
| 383 |
|
| 384 |
def append_parquet_rows(path: Path, new_rows: pd.DataFrame, subset: list[str]) -> pd.DataFrame:
|
|
@@ -396,6 +429,11 @@ def append_parquet_rows(path: Path, new_rows: pd.DataFrame, subset: list[str]) -
|
|
| 396 |
return combined
|
| 397 |
|
| 398 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 399 |
def latest_parquet_date(path: Path) -> date | None:
|
| 400 |
if not path.exists():
|
| 401 |
return None
|
|
@@ -527,6 +565,15 @@ def predict_row(row: pd.DataFrame) -> Prediction:
|
|
| 527 |
is_overridden=is_overridden,
|
| 528 |
)
|
| 529 |
pd.DataFrame([prediction.to_dict()]).to_csv(LATEST_PATH, index=False)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 530 |
return prediction
|
| 531 |
|
| 532 |
|
|
@@ -553,125 +600,239 @@ def latest_saved_prediction() -> dict[str, Any]:
|
|
| 553 |
return dict(_latest_saved_prediction_cached(_file_cache_key(LATEST_PATH), _file_cache_key(MODEL_DIR / "summary.json")))
|
| 554 |
|
| 555 |
|
| 556 |
-
def _latest_saved_prediction_uncached() -> dict[str, Any]:
|
| 557 |
if LATEST_PATH.exists():
|
| 558 |
return pd.read_csv(LATEST_PATH).iloc[-1].to_dict()
|
| 559 |
summary_path = MODEL_DIR / "summary.json"
|
| 560 |
if summary_path.exists():
|
| 561 |
return json.loads(summary_path.read_text(encoding="utf-8"))
|
| 562 |
-
raise FileNotFoundError("No latest prediction is available yet.")
|
| 563 |
-
|
| 564 |
-
|
| 565 |
-
def _read_daily_forecaster_summary() -> dict[str, Any] | None:
|
| 566 |
-
if not DAILY_FORECASTER_SUMMARY_PATH.exists():
|
| 567 |
-
return None
|
| 568 |
-
raw = json.loads(DAILY_FORECASTER_SUMMARY_PATH.read_text(encoding="utf-8"))
|
| 569 |
-
if isinstance(raw, list):
|
| 570 |
-
matches = [row for row in raw if row.get("symbol") == "NIFTY 50"]
|
| 571 |
-
summary = dict(matches[0] if matches else raw[0])
|
| 572 |
-
elif isinstance(raw, dict):
|
| 573 |
-
summary = dict(raw)
|
| 574 |
-
else:
|
| 575 |
-
return None
|
| 576 |
-
config = summary.get("config") if isinstance(summary.get("config"), dict) else {}
|
| 577 |
-
summary.setdefault("symbol", "NIFTY 50")
|
| 578 |
-
summary.setdefault("horizon", "daily")
|
| 579 |
-
summary.setdefault("horizon_bars", 1)
|
| 580 |
-
summary["model_name"] = "nifty_tomorrow_direction_model"
|
| 581 |
-
summary["source_model"] = str(config.get("name") or summary.get("source_model") or "locked_multiwindow_nifty50_ensemble")
|
| 582 |
-
summary["target"] = "next trading session NIFTY 50 direction"
|
| 583 |
-
summary["artifact_type"] = "daily_forecaster_outputs"
|
| 584 |
-
summary["artifact_source"] = str(DAILY_FORECASTER_OUTPUT_DIR)
|
| 585 |
-
return summary
|
| 586 |
-
|
| 587 |
-
|
| 588 |
-
def _read_daily_forecaster_latest(summary: dict[str, Any]) -> dict[str, Any] | None:
|
| 589 |
-
if not DAILY_FORECASTER_LATEST_PATH.exists():
|
| 590 |
-
return None
|
| 591 |
-
latest = pd.read_csv(DAILY_FORECASTER_LATEST_PATH)
|
| 592 |
-
if latest.empty:
|
| 593 |
-
return None
|
| 594 |
-
if "symbol" in latest.columns:
|
| 595 |
-
filtered = latest[latest["symbol"].astype(str) == "NIFTY 50"]
|
| 596 |
-
if not filtered.empty:
|
| 597 |
-
latest = filtered
|
| 598 |
-
row = {k: (None if pd.isna(v) else v) for k, v in latest.iloc[-1].to_dict().items()}
|
| 599 |
-
input_date = row.get("latest_forecast_date") or row.get("input_date")
|
| 600 |
-
target_date = row.get("target_date")
|
| 601 |
-
if not target_date and input_date:
|
| 602 |
-
try:
|
| 603 |
-
target_date = next_trading_day(date.fromisoformat(str(input_date)[:10]) + timedelta(days=1)).isoformat()
|
| 604 |
-
except Exception:
|
| 605 |
-
target_date = None
|
| 606 |
-
prob_up = row.get("latest_forecast_prob_up", row.get("prob_up"))
|
| 607 |
-
prediction = row.get("latest_forecast_signal", row.get("prediction"))
|
| 608 |
-
threshold = row.get("threshold", summary.get("threshold"))
|
| 609 |
-
confidence = row.get("confidence")
|
| 610 |
-
if confidence is None and prob_up is not None:
|
| 611 |
-
try:
|
| 612 |
-
confidence = float(max(float(prob_up), 1.0 - float(prob_up)))
|
| 613 |
-
except Exception:
|
| 614 |
-
confidence = None
|
| 615 |
-
return {
|
| 616 |
-
"input_date": input_date,
|
| 617 |
-
"target_date": target_date,
|
| 618 |
-
"prediction": prediction,
|
| 619 |
-
"prob_up": prob_up,
|
| 620 |
-
"confidence": confidence,
|
| 621 |
-
"threshold": threshold,
|
| 622 |
-
"model_name": "nifty_tomorrow_direction_model",
|
| 623 |
-
"source_model": summary.get("source_model", "locked_multiwindow_nifty50_ensemble"),
|
| 624 |
-
"validation_accuracy": summary.get("validation_accuracy"),
|
| 625 |
-
"test_accuracy": summary.get("test_accuracy"),
|
| 626 |
-
"artifact_source": str(DAILY_FORECASTER_OUTPUT_DIR),
|
| 627 |
-
}
|
| 628 |
-
|
| 629 |
-
|
| 630 |
-
def
|
| 631 |
-
|
| 632 |
-
|
| 633 |
-
|
| 634 |
-
|
| 635 |
-
|
| 636 |
-
|
| 637 |
-
|
| 638 |
-
if
|
| 639 |
-
|
| 640 |
-
|
| 641 |
-
|
| 642 |
-
if
|
| 643 |
-
|
| 644 |
-
|
| 645 |
-
|
| 646 |
-
|
| 647 |
-
|
| 648 |
-
|
| 649 |
-
|
| 650 |
-
|
| 651 |
-
|
| 652 |
-
|
| 653 |
-
|
| 654 |
-
|
| 655 |
-
|
| 656 |
-
|
| 657 |
-
|
| 658 |
-
|
| 659 |
-
|
| 660 |
-
|
| 661 |
-
|
| 662 |
-
|
| 663 |
-
|
| 664 |
-
|
| 665 |
-
|
| 666 |
-
|
| 667 |
-
|
| 668 |
-
|
| 669 |
-
|
| 670 |
-
|
| 671 |
-
|
| 672 |
-
|
| 673 |
-
|
| 674 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 675 |
return {
|
| 676 |
"artifact_type": "daily_forecaster_snapshot",
|
| 677 |
"model_name": summary.get("model_name", "nifty_tomorrow_direction_model"),
|
|
@@ -680,63 +841,63 @@ def load_tomorrow_model_artifact() -> dict[str, Any]:
|
|
| 680 |
}
|
| 681 |
|
| 682 |
|
| 683 |
-
def load_tomorrow_summary() -> dict[str, Any]:
|
| 684 |
-
synced = sync_daily_forecaster_outputs()
|
| 685 |
-
if synced is not None and TOMORROW_SUMMARY_PATH.exists():
|
| 686 |
-
return json.loads(TOMORROW_SUMMARY_PATH.read_text(encoding="utf-8"))
|
| 687 |
-
if TOMORROW_SUMMARY_PATH.exists():
|
| 688 |
-
return json.loads(TOMORROW_SUMMARY_PATH.read_text(encoding="utf-8"))
|
| 689 |
-
return {
|
| 690 |
-
"model_name": "nifty_tomorrow_direction_model",
|
| 691 |
-
"source_model": "locked_multiwindow_nifty50_ensemble",
|
| 692 |
-
"target": "next trading session NIFTY 50 direction",
|
| 693 |
-
"threshold": 0.54,
|
| 694 |
-
"validation_accuracy": 0.5673758865248227,
|
| 695 |
-
"test_accuracy": 0.6451612903225806,
|
| 696 |
-
"baseline_accuracy": 0.5053763440860215,
|
| 697 |
-
"n_test": 186,
|
| 698 |
-
"feature_count": 204,
|
| 699 |
-
}
|
| 700 |
-
|
| 701 |
-
|
| 702 |
-
def latest_tomorrow_prediction() -> dict[str, Any]:
|
| 703 |
-
sync_daily_forecaster_outputs()
|
| 704 |
-
latest_daily = latest_parquet_date(NIFTY_1D_PATH)
|
| 705 |
-
expected_daily = expected_completed_daily_date()
|
| 706 |
-
valid_daily = min(latest_daily, expected_daily) if latest_daily and expected_daily else (expected_daily or latest_daily)
|
| 707 |
-
|
| 708 |
-
if TOMORROW_LATEST_PATH.exists():
|
| 709 |
-
row = pd.read_csv(TOMORROW_LATEST_PATH).iloc[-1].to_dict()
|
| 710 |
-
cleaned = {k: (None if pd.isna(v) else v) for k, v in row.items()}
|
| 711 |
-
try:
|
| 712 |
-
input_day = date.fromisoformat(str(cleaned.get("input_date"))[:10])
|
| 713 |
-
except Exception:
|
| 714 |
-
input_day = None
|
| 715 |
-
if valid_daily is not None and (input_day is None or input_day < valid_daily):
|
| 716 |
-
try:
|
| 717 |
-
refreshed = refresh_tomorrow_prediction(session_date=valid_daily)
|
| 718 |
-
try:
|
| 719 |
-
refreshed_day = date.fromisoformat(str(refreshed.get("input_date"))[:10])
|
| 720 |
-
except Exception:
|
| 721 |
-
refreshed_day = None
|
| 722 |
-
if refreshed_day is not None and refreshed_day >= valid_daily:
|
| 723 |
-
return refreshed
|
| 724 |
-
except Exception:
|
| 725 |
-
pass
|
| 726 |
-
return cleaned
|
| 727 |
-
summary = load_tomorrow_summary()
|
| 728 |
-
try:
|
| 729 |
-
summary_input_day = date.fromisoformat(str(summary.get("latest_forecast_date"))[:10])
|
| 730 |
-
except Exception:
|
| 731 |
-
summary_input_day = None
|
| 732 |
-
if valid_daily is not None and (summary_input_day is None or summary_input_day < valid_daily):
|
| 733 |
-
try:
|
| 734 |
-
return refresh_tomorrow_prediction(session_date=valid_daily)
|
| 735 |
-
except Exception:
|
| 736 |
-
pass
|
| 737 |
-
return {
|
| 738 |
-
"input_date": summary.get("latest_forecast_date"),
|
| 739 |
-
"target_date": None,
|
| 740 |
"prediction": summary.get("latest_forecast_signal"),
|
| 741 |
"prob_up": summary.get("latest_forecast_prob_up"),
|
| 742 |
"confidence": None,
|
|
@@ -892,27 +1053,27 @@ def _apply_tplus1_overlays(pred: np.ndarray, frame: pd.DataFrame, overlays: list
|
|
| 892 |
return adjusted
|
| 893 |
|
| 894 |
|
| 895 |
-
def refresh_tplus1_prediction(session_date: date | None = None) -> dict[str, Any]:
|
| 896 |
-
if not TPLUS1_MODEL_PATH.exists():
|
| 897 |
-
raise FileNotFoundError(f"Missing T+1 model artifact: {TPLUS1_MODEL_PATH}")
|
| 898 |
-
payload = joblib.load(TPLUS1_MODEL_PATH)
|
| 899 |
-
features = payload["features"]
|
| 900 |
-
threshold = float(payload["threshold"])
|
| 901 |
-
frame = _add_tplus1_target_features(_build_tplus1_session_features(_minute_frame_for_tplus1()))
|
| 902 |
-
if session_date is not None:
|
| 903 |
-
row = frame[pd.to_datetime(frame["date"], errors="coerce").dt.date == session_date].tail(1)
|
| 904 |
-
else:
|
| 905 |
-
row = frame.tail(1)
|
| 906 |
-
if row.empty:
|
| 907 |
-
minutes = fetch_yahoo_minutes(period="7d")
|
| 908 |
-
append_parquet_rows(NIFTY_1M_PATH, minutes, ["date"])
|
| 909 |
-
frame = _add_tplus1_target_features(_build_tplus1_session_features(_minute_frame_for_tplus1()))
|
| 910 |
-
if session_date is not None:
|
| 911 |
-
row = frame[pd.to_datetime(frame["date"], errors="coerce").dt.date == session_date].tail(1)
|
| 912 |
-
else:
|
| 913 |
-
row = frame.tail(1)
|
| 914 |
-
if row.empty:
|
| 915 |
-
raise RuntimeError("No complete 14:00-14:20 window is available for T+1 prediction.")
|
| 916 |
missing = [col for col in features if col not in row.columns]
|
| 917 |
if missing:
|
| 918 |
raise RuntimeError(f"T+1 feature row is missing model features: {missing[:5]}")
|
|
@@ -938,8 +1099,10 @@ def refresh_tplus1_prediction(session_date: date | None = None) -> dict[str, Any
|
|
| 938 |
"validation_accuracy": summary.get("validation_accuracy"),
|
| 939 |
"test_accuracy": summary.get("test_accuracy"),
|
| 940 |
"accuracy_goal": summary.get("accuracy_goal"),
|
|
|
|
| 941 |
}
|
| 942 |
pd.DataFrame([out]).to_csv(TPLUS1_LATEST_PATH, index=False)
|
|
|
|
| 943 |
clear_dashboard_payload_cache()
|
| 944 |
return out
|
| 945 |
|
|
@@ -966,23 +1129,26 @@ def _tomorrow_probability_from_daily(daily: pd.DataFrame, fallback_prob: float)
|
|
| 966 |
return float(np.clip(score, 0.35, 0.65))
|
| 967 |
|
| 968 |
|
| 969 |
-
def refresh_tomorrow_prediction(session_date: date | None = None) -> dict[str, Any]:
|
| 970 |
-
|
| 971 |
-
|
| 972 |
-
|
| 973 |
-
|
| 974 |
-
|
| 975 |
-
|
| 976 |
-
|
| 977 |
-
|
| 978 |
-
|
| 979 |
-
|
| 980 |
-
|
| 981 |
-
|
| 982 |
-
|
| 983 |
-
|
| 984 |
-
|
| 985 |
-
|
|
|
|
|
|
|
|
|
|
| 986 |
daily = pd.read_parquet(NIFTY_1D_PATH)
|
| 987 |
daily["date"] = pd.to_datetime(daily["date"], errors="coerce").dt.normalize()
|
| 988 |
daily = daily.dropna(subset=["date"]).sort_values("date")
|
|
@@ -1006,21 +1172,23 @@ def refresh_tomorrow_prediction(session_date: date | None = None) -> dict[str, A
|
|
| 1006 |
"source_model": str(summary.get("source_model", "tuned_daily_forest_single")),
|
| 1007 |
"validation_accuracy": float(summary.get("validation_accuracy", 0.5780141843971631)),
|
| 1008 |
"test_accuracy": float(summary.get("test_accuracy", 0.6182795698924731)),
|
|
|
|
| 1009 |
}
|
| 1010 |
pd.DataFrame([row]).to_csv(TOMORROW_LATEST_PATH, index=False)
|
|
|
|
| 1011 |
summary = dict(summary)
|
| 1012 |
-
summary.update(
|
| 1013 |
-
{
|
| 1014 |
-
"latest_forecast_date": row["input_date"],
|
| 1015 |
"latest_forecast_for": f"next trading session {row['target_date']}",
|
| 1016 |
"latest_forecast_prob_up": row["prob_up"],
|
| 1017 |
"latest_forecast_signal": row["prediction"],
|
| 1018 |
"latest_target_date": row["target_date"],
|
| 1019 |
-
}
|
| 1020 |
-
)
|
| 1021 |
-
TOMORROW_SUMMARY_PATH.write_text(json.dumps(summary, indent=2), encoding="utf-8")
|
| 1022 |
-
clear_dashboard_payload_cache()
|
| 1023 |
-
return row
|
| 1024 |
|
| 1025 |
|
| 1026 |
def _json_ready_frame(df: pd.DataFrame, limit: int | None = None) -> list[dict[str, Any]]:
|
|
@@ -1034,6 +1202,8 @@ def _json_ready_frame(df: pd.DataFrame, limit: int | None = None) -> list[dict[s
|
|
| 1034 |
return out.to_dict(orient="records")
|
| 1035 |
|
| 1036 |
|
|
|
|
|
|
|
| 1037 |
def load_model_summary() -> dict[str, Any]:
|
| 1038 |
summary_path = MODEL_DIR / "summary.json"
|
| 1039 |
if not summary_path.exists():
|
|
@@ -1096,118 +1266,190 @@ def dashboard_payload() -> dict[str, Any]:
|
|
| 1096 |
_file_cache_key(MODEL_DIR / "candidate_results.csv"),
|
| 1097 |
_file_cache_key(NIFTY_1M_PATH),
|
| 1098 |
_file_cache_key(LIVE_ACCURACY_PATH),
|
|
|
|
| 1099 |
)
|
| 1100 |
with _dashboard_payload_lock:
|
| 1101 |
return copy.deepcopy(_dashboard_payload_cached(key))
|
| 1102 |
|
| 1103 |
|
| 1104 |
-
def warm_dashboard_payload_cache() -> None:
|
| 1105 |
-
dashboard_payload()
|
| 1106 |
-
|
| 1107 |
-
|
| 1108 |
-
def
|
| 1109 |
-
|
| 1110 |
-
|
| 1111 |
-
|
| 1112 |
-
|
| 1113 |
-
|
| 1114 |
-
|
| 1115 |
-
|
| 1116 |
-
|
| 1117 |
-
|
| 1118 |
-
|
| 1119 |
-
|
| 1120 |
-
|
| 1121 |
-
|
| 1122 |
-
|
| 1123 |
-
|
| 1124 |
-
|
| 1125 |
-
|
| 1126 |
-
|
| 1127 |
-
|
| 1128 |
-
|
| 1129 |
-
|
| 1130 |
-
|
| 1131 |
-
|
| 1132 |
-
|
| 1133 |
-
|
| 1134 |
-
|
| 1135 |
-
|
| 1136 |
-
|
| 1137 |
-
|
| 1138 |
-
|
| 1139 |
-
|
| 1140 |
-
|
| 1141 |
-
"
|
| 1142 |
-
|
| 1143 |
-
|
| 1144 |
-
|
| 1145 |
-
|
| 1146 |
-
|
| 1147 |
-
|
| 1148 |
-
|
| 1149 |
-
|
| 1150 |
-
|
| 1151 |
-
|
| 1152 |
-
|
| 1153 |
-
|
| 1154 |
-
|
| 1155 |
-
|
| 1156 |
-
|
| 1157 |
-
|
| 1158 |
-
|
| 1159 |
-
|
| 1160 |
-
|
| 1161 |
-
|
| 1162 |
-
|
| 1163 |
-
|
| 1164 |
-
|
| 1165 |
-
|
| 1166 |
-
|
| 1167 |
-
|
| 1168 |
-
|
| 1169 |
-
|
| 1170 |
-
|
| 1171 |
-
|
| 1172 |
-
|
| 1173 |
-
|
| 1174 |
-
|
| 1175 |
-
|
| 1176 |
-
|
| 1177 |
-
|
| 1178 |
-
|
| 1179 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1180 |
summary = load_model_summary()
|
| 1181 |
t5_latest = _latest_saved_prediction_uncached()
|
| 1182 |
tomorrow_summary = load_tomorrow_summary()
|
| 1183 |
tomorrow_latest = latest_tomorrow_prediction()
|
| 1184 |
tplus1_summary = load_tplus1_summary()
|
| 1185 |
tplus1_latest = latest_tplus1_prediction()
|
| 1186 |
-
refresh_state = load_refresh_state()
|
| 1187 |
t5_test = load_test_predictions()
|
| 1188 |
tomorrow_test = load_tomorrow_test_predictions()
|
|
|
|
| 1189 |
tplus1_test = load_tplus1_test_predictions()
|
| 1190 |
daily = pd.read_parquet(NIFTY_1D_PATH)
|
| 1191 |
daily["date"] = pd.to_datetime(daily["date"], errors="coerce")
|
| 1192 |
daily = daily.sort_values("date").tail(180)
|
| 1193 |
-
dataset = read_training_dataset()
|
| 1194 |
-
opening = dataset[["date", "first5_return", "first5_range_pct", "first5_close_location"]].tail(120).copy()
|
| 1195 |
|
| 1196 |
if not t5_test.empty:
|
| 1197 |
-
|
| 1198 |
-
recent_accuracy = float(recent_predictions["correct"].mean())
|
| 1199 |
-
direction_mix = t5_test.groupby("prediction")["correct"].agg(["count", "mean"]).reset_index()
|
| 1200 |
-
monthly = (
|
| 1201 |
-
t5_test.assign(month=t5_test["date"].dt.strftime("%Y-%m"))
|
| 1202 |
-
.groupby("month", as_index=False)["correct"]
|
| 1203 |
-
.mean()
|
| 1204 |
-
.rename(columns={"correct": "accuracy"})
|
| 1205 |
-
)
|
| 1206 |
else:
|
| 1207 |
-
recent_predictions = pd.DataFrame()
|
| 1208 |
recent_accuracy = None
|
| 1209 |
-
direction_mix = pd.DataFrame()
|
| 1210 |
-
monthly = pd.DataFrame()
|
| 1211 |
|
| 1212 |
if not tomorrow_test.empty:
|
| 1213 |
tomorrow_recent = tomorrow_test.tail(40).copy()
|
|
@@ -1217,7 +1459,6 @@ def _dashboard_payload_cached(key: tuple[tuple[str, int | None, int | None], ...
|
|
| 1217 |
tomorrow_recent["correct"] = pd.to_numeric(tomorrow_recent["target"], errors="coerce") == pd.to_numeric(tomorrow_recent["pred"], errors="coerce")
|
| 1218 |
tomorrow_accuracy = float(tomorrow_recent["correct"].mean()) if "correct" in tomorrow_recent.columns else tomorrow_summary.get("test_accuracy")
|
| 1219 |
else:
|
| 1220 |
-
tomorrow_recent = pd.DataFrame()
|
| 1221 |
tomorrow_accuracy = tomorrow_summary.get("test_accuracy")
|
| 1222 |
|
| 1223 |
model_metrics = [
|
|
@@ -1252,59 +1493,46 @@ def _dashboard_payload_cached(key: tuple[tuple[str, int | None, int | None], ...
|
|
| 1252 |
"test_rows": int(len(t5_test)) if not t5_test.empty else int(summary.get("test_rows") or 0),
|
| 1253 |
},
|
| 1254 |
]
|
| 1255 |
-
metrics = {
|
| 1256 |
-
"validation_accuracy": tomorrow_summary.get("validation_accuracy"),
|
| 1257 |
-
"test_accuracy": tomorrow_summary.get("test_accuracy"),
|
| 1258 |
"baseline_test_accuracy": tomorrow_summary.get("baseline_accuracy"),
|
| 1259 |
"validation_auc": summary.get("validation_auc"),
|
| 1260 |
"test_auc": summary.get("test_auc"),
|
| 1261 |
"test_brier": summary.get("test_brier"),
|
| 1262 |
"feature_count": tomorrow_summary.get("feature_count"),
|
| 1263 |
"recent_accuracy": tomorrow_accuracy,
|
| 1264 |
-
"recent_accuracy_days": int(len(
|
| 1265 |
-
"total_test_days": int(tomorrow_summary.get("n_test") or len(tomorrow_test) or 0),
|
| 1266 |
-
"models": model_metrics,
|
| 1267 |
-
}
|
| 1268 |
-
|
| 1269 |
-
|
| 1270 |
-
|
| 1271 |
-
|
| 1272 |
-
|
| 1273 |
-
|
| 1274 |
-
|
| 1275 |
-
|
| 1276 |
-
|
| 1277 |
-
|
| 1278 |
-
|
| 1279 |
-
|
| 1280 |
-
|
| 1281 |
-
|
|
|
|
|
|
|
| 1282 |
"metrics": metrics,
|
| 1283 |
-
"
|
| 1284 |
-
"
|
| 1285 |
-
"tplus1_summary": tplus1_summary,
|
| 1286 |
-
"candidates": load_candidate_results(),
|
| 1287 |
"charts": {
|
| 1288 |
-
"
|
| 1289 |
-
"
|
| 1290 |
-
"
|
| 1291 |
-
"
|
| 1292 |
-
"
|
| 1293 |
-
"
|
| 1294 |
-
"
|
| 1295 |
-
"tplus1_recent_predictions": _json_ready_frame(tplus1_test.tail(40)),
|
| 1296 |
-
"track_record": track_record,
|
| 1297 |
-
},
|
| 1298 |
-
"data_status": {
|
| 1299 |
-
"nifty_1m_rows": int(len(pd.read_parquet(NIFTY_1M_PATH, columns=["date"]))),
|
| 1300 |
-
"nifty_1d_rows": int(len(pd.read_parquet(NIFTY_1D_PATH, columns=["date"]))),
|
| 1301 |
-
"training_rows": int(len(dataset)),
|
| 1302 |
-
"test_prediction_rows": int(len(t5_test)),
|
| 1303 |
-
"tomorrow_test_prediction_rows": int(len(tomorrow_test)),
|
| 1304 |
-
"tplus1_test_prediction_rows": int(len(tplus1_test)),
|
| 1305 |
-
"latest_daily_date": pd.to_datetime(daily["date"]).max().date().isoformat(),
|
| 1306 |
-
"refresh_phase": refresh_state.get("phase", REFRESH_NORMAL),
|
| 1307 |
-
"refresh_state": refresh_state,
|
| 1308 |
},
|
| 1309 |
}
|
| 1310 |
|
|
@@ -1323,14 +1551,12 @@ def refresh_first5_prediction(session_date: date | None = None, minutes: pd.Data
|
|
| 1323 |
merged = merged.drop_duplicates(subset=["date"], keep="last").sort_values("date").reset_index(drop=True)
|
| 1324 |
merged.to_parquet(OPENING_DATASET_PATH, index=False, compression="zstd")
|
| 1325 |
prediction = predict_row(row)
|
| 1326 |
-
clear_dashboard_payload_cache()
|
| 1327 |
return prediction
|
| 1328 |
|
| 1329 |
|
| 1330 |
def refresh_daily_data() -> dict[str, Any]:
|
| 1331 |
daily = fetch_yahoo_daily(period="1mo")
|
| 1332 |
combined = append_parquet_rows(NIFTY_1D_PATH, daily, ["date"])
|
| 1333 |
-
clear_dashboard_payload_cache()
|
| 1334 |
return {
|
| 1335 |
"rows": int(len(combined)),
|
| 1336 |
"latest_date": pd.to_datetime(combined["date"]).max().date().isoformat(),
|
|
@@ -1383,7 +1609,6 @@ def update_opening_outcomes_from_daily() -> dict[str, Any]:
|
|
| 1383 |
dataset = dataset.drop(columns=["_session_date"])
|
| 1384 |
dataset = dataset.sort_values("date").reset_index(drop=True)
|
| 1385 |
dataset.to_parquet(OPENING_DATASET_PATH, index=False, compression="zstd")
|
| 1386 |
-
clear_dashboard_payload_cache()
|
| 1387 |
latest = pd.to_datetime(dataset["date"], errors="coerce").max()
|
| 1388 |
return {
|
| 1389 |
"updated_rows": int(updated),
|
|
@@ -1391,136 +1616,285 @@ def update_opening_outcomes_from_daily() -> dict[str, Any]:
|
|
| 1391 |
}
|
| 1392 |
|
| 1393 |
|
| 1394 |
-
def load_live_accuracy() -> dict[str, Any]:
|
| 1395 |
-
"""Load the live accuracy ledger from disk."""
|
| 1396 |
-
|
| 1397 |
-
|
| 1398 |
-
|
| 1399 |
-
|
| 1400 |
-
|
| 1401 |
-
|
| 1402 |
-
|
| 1403 |
-
|
| 1404 |
-
|
| 1405 |
-
|
| 1406 |
-
|
| 1407 |
-
|
| 1408 |
-
|
| 1409 |
-
|
| 1410 |
-
|
| 1411 |
-
|
| 1412 |
-
|
| 1413 |
-
|
| 1414 |
-
|
| 1415 |
-
|
| 1416 |
-
|
| 1417 |
-
|
| 1418 |
-
|
| 1419 |
-
|
| 1420 |
-
|
| 1421 |
-
|
| 1422 |
-
|
| 1423 |
-
|
| 1424 |
-
|
| 1425 |
-
|
| 1426 |
-
|
| 1427 |
-
|
| 1428 |
-
|
| 1429 |
-
|
| 1430 |
-
|
| 1431 |
-
|
| 1432 |
-
|
| 1433 |
-
|
| 1434 |
-
|
| 1435 |
-
|
| 1436 |
-
|
| 1437 |
-
|
| 1438 |
-
|
| 1439 |
-
|
| 1440 |
-
|
| 1441 |
-
|
| 1442 |
-
|
| 1443 |
-
|
| 1444 |
-
|
| 1445 |
-
|
| 1446 |
-
|
| 1447 |
-
|
| 1448 |
-
|
| 1449 |
-
|
| 1450 |
-
|
| 1451 |
-
|
| 1452 |
-
|
| 1453 |
-
|
| 1454 |
-
|
| 1455 |
-
|
| 1456 |
-
|
| 1457 |
-
|
| 1458 |
-
|
| 1459 |
-
|
| 1460 |
-
|
| 1461 |
-
|
| 1462 |
-
|
| 1463 |
-
|
| 1464 |
-
|
| 1465 |
-
|
| 1466 |
-
|
| 1467 |
-
|
| 1468 |
-
|
| 1469 |
-
|
| 1470 |
-
|
| 1471 |
-
|
| 1472 |
-
|
| 1473 |
-
|
| 1474 |
-
|
| 1475 |
-
|
| 1476 |
-
|
| 1477 |
-
|
| 1478 |
-
|
| 1479 |
-
|
| 1480 |
-
|
| 1481 |
-
|
| 1482 |
-
|
| 1483 |
-
|
| 1484 |
-
|
| 1485 |
-
|
| 1486 |
-
|
| 1487 |
-
|
| 1488 |
-
|
| 1489 |
-
|
| 1490 |
-
|
| 1491 |
-
|
| 1492 |
-
|
| 1493 |
-
|
| 1494 |
-
|
| 1495 |
-
|
| 1496 |
-
|
| 1497 |
-
|
| 1498 |
-
|
| 1499 |
-
|
| 1500 |
-
|
| 1501 |
-
|
| 1502 |
-
|
| 1503 |
-
|
| 1504 |
-
|
| 1505 |
-
|
| 1506 |
-
|
| 1507 |
-
|
| 1508 |
-
|
| 1509 |
-
|
| 1510 |
-
|
| 1511 |
-
|
| 1512 |
-
|
| 1513 |
-
|
| 1514 |
-
|
| 1515 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1516 |
def refresh_market_close_data(session_date: date | None = None) -> dict[str, Any]:
|
| 1517 |
now = datetime.now(IST)
|
| 1518 |
session_date = session_date or now.date()
|
| 1519 |
if not is_trading_day(session_date):
|
| 1520 |
raise RuntimeError(f"{session_date.isoformat()} is not an NSE trading session.")
|
| 1521 |
-
save_refresh_state(REFRESH_WAITING, session_date=session_date)
|
| 1522 |
try:
|
| 1523 |
-
save_refresh_state(REFRESH_REFRESHING, session_date=session_date)
|
| 1524 |
minutes = fetch_yahoo_minutes(period="7d")
|
| 1525 |
minute_frame = append_parquet_rows(NIFTY_1M_PATH, minutes, ["date"])
|
| 1526 |
daily_info = refresh_daily_data()
|
|
@@ -1533,8 +1907,6 @@ def refresh_market_close_data(session_date: date | None = None) -> dict[str, Any
|
|
| 1533 |
tplus1_prediction = refresh_tplus1_prediction(session_date=session_date)
|
| 1534 |
outcomes = update_opening_outcomes_from_daily()
|
| 1535 |
tomorrow_prediction = refresh_tomorrow_prediction(session_date=session_date)
|
| 1536 |
-
state = save_refresh_state(REFRESH_READY, session_date=session_date)
|
| 1537 |
-
clear_dashboard_payload_cache()
|
| 1538 |
return {
|
| 1539 |
"session_date": session_date.isoformat(),
|
| 1540 |
"nifty_1m_rows": int(len(minute_frame)),
|
|
@@ -1544,15 +1916,12 @@ def refresh_market_close_data(session_date: date | None = None) -> dict[str, Any
|
|
| 1544 |
"t5_prediction": t5_prediction.to_dict(),
|
| 1545 |
"tplus1_prediction": tplus1_prediction,
|
| 1546 |
"tomorrow_prediction": tomorrow_prediction,
|
| 1547 |
-
"refresh_state": state,
|
| 1548 |
}
|
| 1549 |
-
except Exception
|
| 1550 |
-
save_refresh_state(REFRESH_FAILED, session_date=session_date, error=str(exc))
|
| 1551 |
-
clear_dashboard_payload_cache()
|
| 1552 |
raise
|
| 1553 |
|
| 1554 |
|
| 1555 |
-
def close_refresh_due(now: datetime | None = None) -> bool:
|
| 1556 |
now = now or datetime.now(IST)
|
| 1557 |
if not is_trading_day(now.date()) or now.time() < CLOSE_REFRESH_READY:
|
| 1558 |
return False
|
|
@@ -1567,137 +1936,140 @@ def close_refresh_due(now: datetime | None = None) -> bool:
|
|
| 1567 |
tomorrow_input = date.fromisoformat(str(tomorrow_latest.get("input_date"))[:10])
|
| 1568 |
except Exception:
|
| 1569 |
tomorrow_input = None
|
| 1570 |
-
return any(
|
| 1571 |
-
latest != now.date()
|
| 1572 |
-
for latest in (latest_daily, latest_minutes, latest_opening, latest_opening_outcome, tomorrow_input)
|
| 1573 |
-
)
|
| 1574 |
-
|
| 1575 |
-
|
| 1576 |
-
def latest_prediction_input_date(path: Path) -> date | None:
|
| 1577 |
-
if not path.exists():
|
| 1578 |
-
return None
|
| 1579 |
-
try:
|
| 1580 |
-
frame = pd.read_csv(path, usecols=["input_date"])
|
| 1581 |
-
except Exception:
|
| 1582 |
-
return None
|
| 1583 |
-
if frame.empty:
|
| 1584 |
-
return None
|
| 1585 |
-
value = pd.to_datetime(frame["input_date"], errors="coerce").max()
|
| 1586 |
-
return None if pd.isna(value) else value.date()
|
| 1587 |
-
|
| 1588 |
-
|
| 1589 |
-
def latest_tomorrow_input_date() -> date | None:
|
| 1590 |
-
try:
|
| 1591 |
-
latest = latest_tomorrow_prediction()
|
| 1592 |
-
raw = latest.get("input_date")
|
| 1593 |
-
return date.fromisoformat(str(raw)[:10]) if raw else None
|
| 1594 |
-
except Exception:
|
| 1595 |
-
return None
|
| 1596 |
-
|
| 1597 |
-
|
| 1598 |
-
def expected_completed_daily_date(now: datetime | None = None) -> date:
|
| 1599 |
-
now = now or datetime.now(IST)
|
| 1600 |
-
if is_trading_day(now.date()) and now.time() < CLOSE_REFRESH_READY:
|
| 1601 |
-
return previous_trading_day(now.date() - timedelta(days=1))
|
| 1602 |
-
return previous_trading_day(now.date())
|
| 1603 |
-
|
| 1604 |
-
|
| 1605 |
-
def expected_minute_date(now: datetime | None = None) -> date:
|
| 1606 |
-
now = now or datetime.now(IST)
|
| 1607 |
-
if is_trading_day(now.date()) and now.time() >= FIRST5_READY:
|
| 1608 |
-
return now.date()
|
| 1609 |
-
return previous_trading_day(now.date() - timedelta(days=1))
|
| 1610 |
-
|
| 1611 |
-
|
| 1612 |
-
def expected_tplus1_date(now: datetime | None = None) -> date:
|
| 1613 |
-
now = now or datetime.now(IST)
|
| 1614 |
-
if is_trading_day(now.date()) and now.time() >= TPLUS1_READY:
|
| 1615 |
-
return now.date()
|
| 1616 |
-
return previous_trading_day(now.date() - timedelta(days=1))
|
| 1617 |
-
|
| 1618 |
-
|
| 1619 |
-
def is_stale(latest: date | None, expected: date) -> bool:
|
| 1620 |
-
return latest is None or latest < expected
|
| 1621 |
-
|
| 1622 |
-
|
| 1623 |
-
def stale_data_status(now: datetime | None = None) -> dict[str, Any]:
|
| 1624 |
-
now = now or datetime.now(IST)
|
| 1625 |
-
expected_daily = expected_completed_daily_date(now)
|
| 1626 |
-
expected_minutes = expected_minute_date(now)
|
| 1627 |
-
expected_tplus1 = expected_tplus1_date(now)
|
| 1628 |
-
|
| 1629 |
-
|
| 1630 |
-
latest_t5 = latest_prediction_input_date(LATEST_PATH)
|
| 1631 |
-
latest_tomorrow = latest_tomorrow_input_date()
|
| 1632 |
-
latest_tplus1 = latest_prediction_input_date(TPLUS1_LATEST_PATH)
|
| 1633 |
-
return {
|
| 1634 |
-
"
|
| 1635 |
-
"
|
| 1636 |
-
"
|
| 1637 |
-
"
|
| 1638 |
-
"
|
| 1639 |
-
|
| 1640 |
-
|
| 1641 |
-
|
| 1642 |
-
|
| 1643 |
-
|
| 1644 |
-
|
| 1645 |
-
|
| 1646 |
-
"
|
| 1647 |
-
|
| 1648 |
-
|
| 1649 |
-
|
| 1650 |
-
|
| 1651 |
-
|
| 1652 |
-
|
| 1653 |
-
|
| 1654 |
-
|
| 1655 |
-
|
| 1656 |
-
|
| 1657 |
-
|
| 1658 |
-
|
| 1659 |
-
|
| 1660 |
-
|
| 1661 |
-
|
| 1662 |
-
|
| 1663 |
-
|
| 1664 |
-
|
| 1665 |
-
|
| 1666 |
-
|
| 1667 |
-
|
| 1668 |
-
|
| 1669 |
-
|
| 1670 |
-
|
| 1671 |
-
|
| 1672 |
-
|
| 1673 |
-
|
| 1674 |
-
|
| 1675 |
-
|
| 1676 |
-
|
| 1677 |
-
|
| 1678 |
-
|
| 1679 |
-
|
| 1680 |
-
|
| 1681 |
-
|
| 1682 |
-
|
| 1683 |
-
|
| 1684 |
-
|
| 1685 |
-
|
| 1686 |
-
|
| 1687 |
-
|
| 1688 |
-
|
| 1689 |
-
|
| 1690 |
-
|
| 1691 |
-
|
| 1692 |
-
|
| 1693 |
-
|
| 1694 |
-
|
| 1695 |
-
|
| 1696 |
-
|
| 1697 |
-
|
| 1698 |
-
|
| 1699 |
-
|
| 1700 |
-
|
|
|
|
|
|
|
|
|
|
| 1701 |
now = now or datetime.now(IST)
|
| 1702 |
target_day = now.date()
|
| 1703 |
if now >= datetime.combine(target_day, run_time, tzinfo=IST):
|
|
|
|
| 1 |
from __future__ import annotations
|
| 2 |
|
| 3 |
+
import json
|
| 4 |
+
import copy
|
| 5 |
+
import os
|
| 6 |
+
import sys
|
| 7 |
+
import threading
|
| 8 |
from dataclasses import dataclass
|
| 9 |
from datetime import date, datetime, time, timedelta
|
| 10 |
from functools import lru_cache
|
|
|
|
| 12 |
from typing import Any
|
| 13 |
from zoneinfo import ZoneInfo
|
| 14 |
|
| 15 |
+
import joblib
|
| 16 |
+
import numpy as np
|
| 17 |
+
import pandas as pd
|
| 18 |
+
from nifty_backend.yahoo_history_client import YahooHistoryClient
|
| 19 |
|
| 20 |
try:
|
| 21 |
import pandas_market_calendars as mcal
|
|
|
|
| 24 |
|
| 25 |
|
| 26 |
IST = ZoneInfo("Asia/Kolkata")
|
| 27 |
+
YAHOO_NIFTY_SYMBOL = "^NSEI"
|
| 28 |
+
MARKET_CLOSE = time(15, 30)
|
| 29 |
+
FIRST5_READY = time(9, 20)
|
| 30 |
+
CLOSE_REFRESH_READY = time(15, 45)
|
| 31 |
+
TPLUS1_READY = time(14, 30)
|
| 32 |
+
STALE_CHECK_INTERVAL_SECONDS = 5
|
| 33 |
+
BACKEND_ROOT = Path(__file__).resolve().parents[1]
|
| 34 |
+
DATA_DIR = BACKEND_ROOT / "data"
|
| 35 |
+
MODEL_DIR = BACKEND_ROOT / "models"
|
| 36 |
+
YAHOO_CACHE_PATH = MODEL_DIR / "yahoo_history_cache.sqlite3"
|
| 37 |
OPENING_DATASET_PATH = DATA_DIR / "opening_direction_training_dataset.parquet"
|
| 38 |
NIFTY_1M_PATH = DATA_DIR / "nifty50_1m.parquet"
|
| 39 |
NIFTY_1D_PATH = DATA_DIR / "nifty50_1d.parquet"
|
|
|
|
| 43 |
TOMORROW_MODEL_PATH = MODEL_DIR / "nifty_tomorrow_direction_model.joblib"
|
| 44 |
TOMORROW_LATEST_PATH = MODEL_DIR / "tomorrow_latest_prediction.csv"
|
| 45 |
TOMORROW_SUMMARY_PATH = MODEL_DIR / "tomorrow_summary.json"
|
| 46 |
+
TOMORROW_TEST_PREDICTIONS_PATH = DATA_DIR / "tomorrow_test_predictions.parquet"
|
| 47 |
+
TOMORROW_PREDICTION_HISTORY_PATH = MODEL_DIR / "tomorrow_prediction_history.parquet"
|
| 48 |
+
FORECASTING_PROJECT_ROOT = Path(
|
| 49 |
+
os.environ.get(
|
| 50 |
+
"FORECASTING_PROJECT_ROOT",
|
| 51 |
+
str(BACKEND_ROOT.parent.parent / "forecasting project"),
|
| 52 |
+
)
|
| 53 |
+
)
|
| 54 |
+
DAILY_FORECASTER_OUTPUT_DIR = MODEL_DIR / "nifty_forecaster" / "outputs"
|
| 55 |
+
DAILY_FORECASTER_SUMMARY_PATH = DAILY_FORECASTER_OUTPUT_DIR / "forecaster_summary.json"
|
| 56 |
+
DAILY_FORECASTER_LATEST_PATH = DAILY_FORECASTER_OUTPUT_DIR / "forecaster_latest.csv"
|
| 57 |
+
DAILY_FORECASTER_PREDICTIONS_PATH = DAILY_FORECASTER_OUTPUT_DIR / "forecaster_test_predictions.csv"
|
| 58 |
+
MFE_SOURCE_OUTPUT_DIR = FORECASTING_PROJECT_ROOT / "Code" / "models" / "nifty_opening_mfe_regressor" / "outputs"
|
| 59 |
+
MFE_OUTPUT_DIR = MODEL_DIR / "nifty_opening_mfe_regressor" / "outputs"
|
| 60 |
+
MFE_SUMMARY_PATH = MFE_OUTPUT_DIR / "summary.json"
|
| 61 |
+
MFE_LATEST_PATH = MFE_OUTPUT_DIR / "latest_prediction.csv"
|
| 62 |
+
MFE_TEST_PREDICTIONS_PATH = MFE_OUTPUT_DIR / "test_predictions.csv"
|
| 63 |
+
TPLUS1_MODEL_PATH = MODEL_DIR / "nifty_1420_tplus1_logistic_model.joblib"
|
| 64 |
TPLUS1_LATEST_PATH = MODEL_DIR / "tplus1_latest_prediction.csv"
|
| 65 |
TPLUS1_SUMMARY_PATH = MODEL_DIR / "tplus1_summary.json"
|
| 66 |
TPLUS1_TEST_PREDICTIONS_PATH = DATA_DIR / "tplus1_test_predictions.parquet"
|
| 67 |
+
TPLUS1_PREDICTION_HISTORY_PATH = MODEL_DIR / "tplus1_prediction_history.parquet"
|
| 68 |
+
T5_PREDICTION_HISTORY_PATH = MODEL_DIR / "t5_prediction_history.parquet"
|
| 69 |
REFRESH_STATE_PATH = MODEL_DIR / "refresh_state.json"
|
| 70 |
REFRESH_WAITING = "waiting_second_payload"
|
| 71 |
REFRESH_REFRESHING = "refreshing"
|
|
|
|
| 89 |
},
|
| 90 |
]
|
| 91 |
|
| 92 |
+
_dashboard_payload_lock = threading.Lock()
|
| 93 |
+
_stale_refresh_lock = threading.Lock()
|
| 94 |
|
| 95 |
|
| 96 |
def utc_now_iso() -> str:
|
|
|
|
| 187 |
return pd.Timestamp(schedule.index[-1]).date()
|
| 188 |
|
| 189 |
|
| 190 |
+
def last_n_trading_sessions(end_day: date, count: int) -> list[date]:
|
| 191 |
+
"""Return the last ``count`` NSE sessions ending on (or before) ``end_day``."""
|
| 192 |
+
sessions: list[date] = []
|
| 193 |
+
cursor = end_day
|
| 194 |
+
guard = 0
|
| 195 |
+
while len(sessions) < count and guard < count * 12:
|
| 196 |
+
guard += 1
|
| 197 |
+
if is_trading_day(cursor):
|
| 198 |
+
sessions.append(cursor)
|
| 199 |
+
if len(sessions) >= count:
|
| 200 |
+
break
|
| 201 |
+
cursor = previous_trading_day(cursor - timedelta(days=1))
|
| 202 |
+
sessions.reverse()
|
| 203 |
+
return sessions
|
| 204 |
+
|
| 205 |
+
|
| 206 |
+
def _track_record_end_session(now: datetime | None = None) -> date:
|
| 207 |
+
"""Latest session the track record should score (today after the close refresh window)."""
|
| 208 |
+
now = now or datetime.now(IST)
|
| 209 |
+
today = now.date()
|
| 210 |
+
if is_trading_day(today) and now.time() >= CLOSE_REFRESH_READY:
|
| 211 |
+
return today
|
| 212 |
+
return expected_completed_daily_date(now)
|
| 213 |
+
|
| 214 |
+
|
| 215 |
class ProbabilityBlend:
|
| 216 |
def __init__(self, models: list[Any], weights: np.ndarray):
|
| 217 |
self.models = models
|
|
|
|
| 311 |
return df.sort_values("date").reset_index(drop=True)
|
| 312 |
|
| 313 |
|
| 314 |
+
def normalize_yahoo_frame(df: pd.DataFrame) -> pd.DataFrame:
|
| 315 |
if df.empty:
|
| 316 |
return pd.DataFrame(columns=["date", "open", "high", "low", "close", "volume"])
|
| 317 |
if isinstance(df.columns, pd.MultiIndex):
|
|
|
|
| 337 |
for src, dst in rename.items():
|
| 338 |
if src in df.columns and dst not in out.columns:
|
| 339 |
out[dst] = pd.to_numeric(df[src], errors="coerce")
|
| 340 |
+
return out.dropna(subset=["date", "open", "high", "low", "close"]).sort_values("date")
|
| 341 |
+
|
| 342 |
+
|
| 343 |
+
@lru_cache(maxsize=1)
|
| 344 |
+
def yahoo_history_client() -> YahooHistoryClient:
|
| 345 |
+
return YahooHistoryClient(cache_path=YAHOO_CACHE_PATH)
|
| 346 |
+
|
| 347 |
+
|
| 348 |
+
def period_start(period: str, *, end: datetime) -> datetime:
|
| 349 |
+
text = str(period).strip().lower()
|
| 350 |
+
units = {
|
| 351 |
+
"d": "days",
|
| 352 |
+
"wk": "weeks",
|
| 353 |
+
"mo": "months",
|
| 354 |
+
"y": "years",
|
| 355 |
+
}
|
| 356 |
+
for suffix, unit in units.items():
|
| 357 |
+
if text.endswith(suffix):
|
| 358 |
+
raw_value = text[: -len(suffix)]
|
| 359 |
+
if not raw_value.isdigit():
|
| 360 |
+
break
|
| 361 |
+
value = int(raw_value)
|
| 362 |
+
if unit == "days":
|
| 363 |
+
return end - timedelta(days=value)
|
| 364 |
+
if unit == "weeks":
|
| 365 |
+
return end - timedelta(weeks=value)
|
| 366 |
+
if unit == "months":
|
| 367 |
+
return end - timedelta(days=value * 31)
|
| 368 |
+
if unit == "years":
|
| 369 |
+
return end - timedelta(days=value * 366)
|
| 370 |
+
raise ValueError(f"Unsupported Yahoo period: {period!r}")
|
| 371 |
+
|
| 372 |
+
|
| 373 |
+
def yahoo_history_to_ohlcv(frame: pd.DataFrame, *, daily: bool) -> pd.DataFrame:
|
| 374 |
+
if frame.empty:
|
| 375 |
+
return pd.DataFrame(columns=["date", "open", "high", "low", "close", "volume"])
|
| 376 |
+
out = frame.rename(columns={"timestamp": "date"}).copy()
|
| 377 |
+
out["date"] = pd.to_datetime(out["date"], errors="coerce")
|
| 378 |
+
if daily:
|
| 379 |
+
out["date"] = out["date"].dt.normalize()
|
| 380 |
+
for column in ("open", "high", "low", "close", "volume"):
|
| 381 |
+
out[column] = pd.to_numeric(out[column], errors="coerce")
|
| 382 |
+
return (
|
| 383 |
+
out[["date", "open", "high", "low", "close", "volume"]]
|
| 384 |
+
.dropna(subset=["date", "open", "high", "low", "close"])
|
| 385 |
+
.drop_duplicates("date", keep="last")
|
| 386 |
+
.sort_values("date")
|
| 387 |
+
.reset_index(drop=True)
|
| 388 |
+
)
|
| 389 |
+
|
| 390 |
+
|
| 391 |
+
def fetch_yahoo_minutes(period: str = "5d") -> pd.DataFrame:
|
| 392 |
+
end = datetime.now(IST).replace(tzinfo=None) + timedelta(minutes=5)
|
| 393 |
+
start = period_start(period, end=end)
|
| 394 |
+
raw = yahoo_history_client().fetch_history(
|
| 395 |
+
YAHOO_NIFTY_SYMBOL,
|
| 396 |
+
interval="1m",
|
| 397 |
+
start=start,
|
| 398 |
+
end=end,
|
| 399 |
+
include_prepost=False,
|
| 400 |
+
)
|
| 401 |
+
return yahoo_history_to_ohlcv(raw, daily=False)
|
| 402 |
+
|
| 403 |
+
|
| 404 |
+
def fetch_yahoo_daily(period: str = "1mo") -> pd.DataFrame:
|
| 405 |
+
end = datetime.now(IST).replace(tzinfo=None) + timedelta(days=1)
|
| 406 |
+
start = period_start(period, end=end)
|
| 407 |
+
raw = yahoo_history_client().fetch_history(
|
| 408 |
+
YAHOO_NIFTY_SYMBOL,
|
| 409 |
+
interval="1d",
|
| 410 |
+
start=start,
|
| 411 |
+
end=end,
|
| 412 |
+
include_prepost=False,
|
| 413 |
+
)
|
| 414 |
+
return yahoo_history_to_ohlcv(raw, daily=True)
|
| 415 |
|
| 416 |
|
| 417 |
def append_parquet_rows(path: Path, new_rows: pd.DataFrame, subset: list[str]) -> pd.DataFrame:
|
|
|
|
| 429 |
return combined
|
| 430 |
|
| 431 |
|
| 432 |
+
def append_prediction_history(path: Path, row: dict[str, Any], subset: list[str]) -> pd.DataFrame:
|
| 433 |
+
frame = pd.DataFrame([row])
|
| 434 |
+
return append_parquet_rows(path, frame, subset)
|
| 435 |
+
|
| 436 |
+
|
| 437 |
def latest_parquet_date(path: Path) -> date | None:
|
| 438 |
if not path.exists():
|
| 439 |
return None
|
|
|
|
| 565 |
is_overridden=is_overridden,
|
| 566 |
)
|
| 567 |
pd.DataFrame([prediction.to_dict()]).to_csv(LATEST_PATH, index=False)
|
| 568 |
+
_record_prediction_history(
|
| 569 |
+
T5_PREDICTION_HISTORY_PATH,
|
| 570 |
+
{
|
| 571 |
+
**prediction.to_dict(),
|
| 572 |
+
"target_date": prediction.input_date,
|
| 573 |
+
"source": "live",
|
| 574 |
+
},
|
| 575 |
+
["target_date"],
|
| 576 |
+
)
|
| 577 |
return prediction
|
| 578 |
|
| 579 |
|
|
|
|
| 600 |
return dict(_latest_saved_prediction_cached(_file_cache_key(LATEST_PATH), _file_cache_key(MODEL_DIR / "summary.json")))
|
| 601 |
|
| 602 |
|
| 603 |
+
def _latest_saved_prediction_uncached() -> dict[str, Any]:
|
| 604 |
if LATEST_PATH.exists():
|
| 605 |
return pd.read_csv(LATEST_PATH).iloc[-1].to_dict()
|
| 606 |
summary_path = MODEL_DIR / "summary.json"
|
| 607 |
if summary_path.exists():
|
| 608 |
return json.loads(summary_path.read_text(encoding="utf-8"))
|
| 609 |
+
raise FileNotFoundError("No latest prediction is available yet.")
|
| 610 |
+
|
| 611 |
+
|
| 612 |
+
def _read_daily_forecaster_summary() -> dict[str, Any] | None:
|
| 613 |
+
if not DAILY_FORECASTER_SUMMARY_PATH.exists():
|
| 614 |
+
return None
|
| 615 |
+
raw = json.loads(DAILY_FORECASTER_SUMMARY_PATH.read_text(encoding="utf-8"))
|
| 616 |
+
if isinstance(raw, list):
|
| 617 |
+
matches = [row for row in raw if row.get("symbol") == "NIFTY 50"]
|
| 618 |
+
summary = dict(matches[0] if matches else raw[0])
|
| 619 |
+
elif isinstance(raw, dict):
|
| 620 |
+
summary = dict(raw)
|
| 621 |
+
else:
|
| 622 |
+
return None
|
| 623 |
+
config = summary.get("config") if isinstance(summary.get("config"), dict) else {}
|
| 624 |
+
summary.setdefault("symbol", "NIFTY 50")
|
| 625 |
+
summary.setdefault("horizon", "daily")
|
| 626 |
+
summary.setdefault("horizon_bars", 1)
|
| 627 |
+
summary["model_name"] = "nifty_tomorrow_direction_model"
|
| 628 |
+
summary["source_model"] = str(config.get("name") or summary.get("source_model") or "locked_multiwindow_nifty50_ensemble")
|
| 629 |
+
summary["target"] = "next trading session NIFTY 50 direction"
|
| 630 |
+
summary["artifact_type"] = "daily_forecaster_outputs"
|
| 631 |
+
summary["artifact_source"] = str(DAILY_FORECASTER_OUTPUT_DIR)
|
| 632 |
+
return summary
|
| 633 |
+
|
| 634 |
+
|
| 635 |
+
def _read_daily_forecaster_latest(summary: dict[str, Any]) -> dict[str, Any] | None:
|
| 636 |
+
if not DAILY_FORECASTER_LATEST_PATH.exists():
|
| 637 |
+
return None
|
| 638 |
+
latest = pd.read_csv(DAILY_FORECASTER_LATEST_PATH)
|
| 639 |
+
if latest.empty:
|
| 640 |
+
return None
|
| 641 |
+
if "symbol" in latest.columns:
|
| 642 |
+
filtered = latest[latest["symbol"].astype(str) == "NIFTY 50"]
|
| 643 |
+
if not filtered.empty:
|
| 644 |
+
latest = filtered
|
| 645 |
+
row = {k: (None if pd.isna(v) else v) for k, v in latest.iloc[-1].to_dict().items()}
|
| 646 |
+
input_date = row.get("latest_forecast_date") or row.get("input_date")
|
| 647 |
+
target_date = row.get("target_date")
|
| 648 |
+
if not target_date and input_date:
|
| 649 |
+
try:
|
| 650 |
+
target_date = next_trading_day(date.fromisoformat(str(input_date)[:10]) + timedelta(days=1)).isoformat()
|
| 651 |
+
except Exception:
|
| 652 |
+
target_date = None
|
| 653 |
+
prob_up = row.get("latest_forecast_prob_up", row.get("prob_up"))
|
| 654 |
+
prediction = row.get("latest_forecast_signal", row.get("prediction"))
|
| 655 |
+
threshold = row.get("threshold", summary.get("threshold"))
|
| 656 |
+
confidence = row.get("confidence")
|
| 657 |
+
if confidence is None and prob_up is not None:
|
| 658 |
+
try:
|
| 659 |
+
confidence = float(max(float(prob_up), 1.0 - float(prob_up)))
|
| 660 |
+
except Exception:
|
| 661 |
+
confidence = None
|
| 662 |
+
return {
|
| 663 |
+
"input_date": input_date,
|
| 664 |
+
"target_date": target_date,
|
| 665 |
+
"prediction": prediction,
|
| 666 |
+
"prob_up": prob_up,
|
| 667 |
+
"confidence": confidence,
|
| 668 |
+
"threshold": threshold,
|
| 669 |
+
"model_name": "nifty_tomorrow_direction_model",
|
| 670 |
+
"source_model": summary.get("source_model", "locked_multiwindow_nifty50_ensemble"),
|
| 671 |
+
"validation_accuracy": summary.get("validation_accuracy"),
|
| 672 |
+
"test_accuracy": summary.get("test_accuracy"),
|
| 673 |
+
"artifact_source": str(DAILY_FORECASTER_OUTPUT_DIR),
|
| 674 |
+
}
|
| 675 |
+
|
| 676 |
+
|
| 677 |
+
def _parse_iso_date(value: Any) -> date | None:
|
| 678 |
+
try:
|
| 679 |
+
return date.fromisoformat(str(value or "")[:10])
|
| 680 |
+
except Exception:
|
| 681 |
+
return None
|
| 682 |
+
|
| 683 |
+
|
| 684 |
+
def _archive_tomorrow_latest_to_history() -> None:
|
| 685 |
+
if not TOMORROW_LATEST_PATH.exists():
|
| 686 |
+
return
|
| 687 |
+
try:
|
| 688 |
+
row = pd.read_csv(TOMORROW_LATEST_PATH).iloc[-1].to_dict()
|
| 689 |
+
cleaned = {k: (None if pd.isna(v) else v) for k, v in row.items()}
|
| 690 |
+
pred = str(cleaned.get("prediction", "")).upper()
|
| 691 |
+
if pred in {"UP", "DOWN"} and cleaned.get("target_date"):
|
| 692 |
+
_record_prediction_history(TOMORROW_PREDICTION_HISTORY_PATH, cleaned, ["target_date"])
|
| 693 |
+
except Exception:
|
| 694 |
+
pass
|
| 695 |
+
|
| 696 |
+
|
| 697 |
+
def _tomorrow_actual_outcome(
|
| 698 |
+
target_day: date,
|
| 699 |
+
day_close: float,
|
| 700 |
+
closes_by_date: dict[date, float],
|
| 701 |
+
) -> tuple[float | None, str | None]:
|
| 702 |
+
"""Return (move, direction) for Tomorrow scoring: close vs previous session close."""
|
| 703 |
+
prev_day = previous_trading_day(target_day - timedelta(days=1))
|
| 704 |
+
prev_close = closes_by_date.get(prev_day)
|
| 705 |
+
if prev_close is None or not np.isfinite(prev_close) or prev_close == 0:
|
| 706 |
+
return None, None
|
| 707 |
+
actual_move = (day_close - prev_close) / prev_close
|
| 708 |
+
actual_direction = "UP" if day_close > prev_close else "DOWN"
|
| 709 |
+
return actual_move, actual_direction
|
| 710 |
+
|
| 711 |
+
|
| 712 |
+
def _find_tomorrow_prediction_for_target(target_day: date) -> dict[str, Any] | None:
|
| 713 |
+
"""Return the Tomorrow prediction that targets ``target_day``."""
|
| 714 |
+
target_iso = target_day.isoformat()
|
| 715 |
+
tom_history = _load_prediction_history(TOMORROW_PREDICTION_HISTORY_PATH)
|
| 716 |
+
if not tom_history.empty:
|
| 717 |
+
for col in ("date", "input_date", "target_date", "forecast_date"):
|
| 718 |
+
if col in tom_history.columns:
|
| 719 |
+
tom_history[col] = pd.to_datetime(tom_history[col], errors="coerce")
|
| 720 |
+
|
| 721 |
+
if not tom_history.empty and "target_date" in tom_history.columns:
|
| 722 |
+
rows = tom_history[tom_history["target_date"].dt.date == target_day]
|
| 723 |
+
if not rows.empty:
|
| 724 |
+
return rows.iloc[-1].to_dict()
|
| 725 |
+
|
| 726 |
+
if TOMORROW_LATEST_PATH.exists():
|
| 727 |
+
try:
|
| 728 |
+
row = pd.read_csv(TOMORROW_LATEST_PATH).iloc[-1].to_dict()
|
| 729 |
+
if _parse_iso_date(row.get("target_date")) == target_day:
|
| 730 |
+
return row
|
| 731 |
+
except Exception:
|
| 732 |
+
pass
|
| 733 |
+
|
| 734 |
+
input_day = previous_trading_day(target_day - timedelta(days=1))
|
| 735 |
+
if not tom_history.empty and "input_date" in tom_history.columns:
|
| 736 |
+
rows = tom_history[tom_history["input_date"].dt.date == input_day]
|
| 737 |
+
if not rows.empty:
|
| 738 |
+
row = rows.iloc[-1].to_dict()
|
| 739 |
+
if _parse_iso_date(row.get("target_date")) in {None, target_day}:
|
| 740 |
+
return row
|
| 741 |
+
|
| 742 |
+
if TOMORROW_LATEST_PATH.exists():
|
| 743 |
+
try:
|
| 744 |
+
row = pd.read_csv(TOMORROW_LATEST_PATH).iloc[-1].to_dict()
|
| 745 |
+
if _parse_iso_date(row.get("input_date")) == input_day:
|
| 746 |
+
return row
|
| 747 |
+
except Exception:
|
| 748 |
+
pass
|
| 749 |
+
|
| 750 |
+
tomorrow_test = load_tomorrow_test_predictions()
|
| 751 |
+
tomorrow_history = _load_prediction_history(TOMORROW_PREDICTION_HISTORY_PATH)
|
| 752 |
+
if not tomorrow_test.empty:
|
| 753 |
+
for col in ("target_date", "date"):
|
| 754 |
+
if col in tomorrow_test.columns:
|
| 755 |
+
test_dates = pd.to_datetime(tomorrow_test[col], errors="coerce").dt.date
|
| 756 |
+
rows = tomorrow_test[test_dates == target_day]
|
| 757 |
+
if not rows.empty:
|
| 758 |
+
return rows.iloc[-1].to_dict()
|
| 759 |
+
|
| 760 |
+
ledger = load_live_accuracy()
|
| 761 |
+
for entry in ledger.get("tomorrow", {}).get("entries", []):
|
| 762 |
+
if str(entry.get("date", ""))[:10] == target_iso:
|
| 763 |
+
pred = str(entry.get("prediction", "")).upper()
|
| 764 |
+
if pred in {"UP", "DOWN"}:
|
| 765 |
+
return {
|
| 766 |
+
"target_date": target_iso,
|
| 767 |
+
"prediction": pred,
|
| 768 |
+
"source": entry.get("source", "live"),
|
| 769 |
+
}
|
| 770 |
+
return None
|
| 771 |
+
|
| 772 |
+
|
| 773 |
+
def sync_daily_forecaster_outputs() -> dict[str, Any] | None:
|
| 774 |
+
summary = _read_daily_forecaster_summary()
|
| 775 |
+
if summary is None:
|
| 776 |
+
return None
|
| 777 |
+
latest = _read_daily_forecaster_latest(summary)
|
| 778 |
+
TOMORROW_SUMMARY_PATH.write_text(json.dumps(summary, indent=2), encoding="utf-8")
|
| 779 |
+
if latest is not None:
|
| 780 |
+
_archive_tomorrow_latest_to_history()
|
| 781 |
+
keep_existing = False
|
| 782 |
+
if TOMORROW_LATEST_PATH.exists():
|
| 783 |
+
try:
|
| 784 |
+
existing = pd.read_csv(TOMORROW_LATEST_PATH).iloc[-1].to_dict()
|
| 785 |
+
existing_input = _parse_iso_date(existing.get("input_date"))
|
| 786 |
+
forecaster_input = _parse_iso_date(latest.get("input_date"))
|
| 787 |
+
existing_pred = str(existing.get("prediction", "")).upper()
|
| 788 |
+
if (
|
| 789 |
+
existing_input is not None
|
| 790 |
+
and forecaster_input is not None
|
| 791 |
+
and existing_input > forecaster_input
|
| 792 |
+
and existing_pred in {"UP", "DOWN"}
|
| 793 |
+
):
|
| 794 |
+
keep_existing = True
|
| 795 |
+
except Exception:
|
| 796 |
+
keep_existing = False
|
| 797 |
+
if not keep_existing:
|
| 798 |
+
pd.DataFrame([latest]).to_csv(TOMORROW_LATEST_PATH, index=False)
|
| 799 |
+
if DAILY_FORECASTER_PREDICTIONS_PATH.exists():
|
| 800 |
+
predictions = pd.read_csv(DAILY_FORECASTER_PREDICTIONS_PATH)
|
| 801 |
+
if "symbol" in predictions.columns:
|
| 802 |
+
predictions = predictions[predictions["symbol"].astype(str) == "NIFTY 50"].copy()
|
| 803 |
+
if not predictions.empty:
|
| 804 |
+
if "pred" in predictions.columns and "prediction" not in predictions.columns:
|
| 805 |
+
predictions["prediction"] = np.where(pd.to_numeric(predictions["pred"], errors="coerce") == 1, "UP", "DOWN")
|
| 806 |
+
if "correct" not in predictions.columns and {"target", "pred"}.issubset(predictions.columns):
|
| 807 |
+
predictions["correct"] = (
|
| 808 |
+
pd.to_numeric(predictions["target"], errors="coerce")
|
| 809 |
+
== pd.to_numeric(predictions["pred"], errors="coerce")
|
| 810 |
+
)
|
| 811 |
+
predictions.to_parquet(TOMORROW_TEST_PREDICTIONS_PATH, index=False)
|
| 812 |
+
artifact = {
|
| 813 |
+
"artifact_type": "daily_forecaster_outputs",
|
| 814 |
+
"model_name": "nifty_tomorrow_direction_model",
|
| 815 |
+
"source_model": summary.get("source_model", "locked_multiwindow_nifty50_ensemble"),
|
| 816 |
+
"threshold": float(summary.get("threshold", 0.54)),
|
| 817 |
+
"validation_accuracy": summary.get("validation_accuracy"),
|
| 818 |
+
"test_accuracy": summary.get("test_accuracy"),
|
| 819 |
+
"validation_prob_std": summary.get("validation_prob_std"),
|
| 820 |
+
"test_prob_std": summary.get("test_prob_std"),
|
| 821 |
+
"test_prob_min": summary.get("test_prob_min"),
|
| 822 |
+
"test_prob_max": summary.get("test_prob_max"),
|
| 823 |
+
"artifact_source": str(DAILY_FORECASTER_OUTPUT_DIR),
|
| 824 |
+
}
|
| 825 |
+
joblib.dump(artifact, TOMORROW_MODEL_PATH)
|
| 826 |
+
return latest or summary
|
| 827 |
+
|
| 828 |
+
|
| 829 |
+
def load_tomorrow_model_artifact() -> dict[str, Any]:
|
| 830 |
+
synced = sync_daily_forecaster_outputs()
|
| 831 |
+
if synced is not None and TOMORROW_MODEL_PATH.exists():
|
| 832 |
+
return joblib.load(TOMORROW_MODEL_PATH)
|
| 833 |
+
if TOMORROW_MODEL_PATH.exists():
|
| 834 |
+
return joblib.load(TOMORROW_MODEL_PATH)
|
| 835 |
+
summary = load_tomorrow_summary()
|
| 836 |
return {
|
| 837 |
"artifact_type": "daily_forecaster_snapshot",
|
| 838 |
"model_name": summary.get("model_name", "nifty_tomorrow_direction_model"),
|
|
|
|
| 841 |
}
|
| 842 |
|
| 843 |
|
| 844 |
+
def load_tomorrow_summary() -> dict[str, Any]:
|
| 845 |
+
synced = sync_daily_forecaster_outputs()
|
| 846 |
+
if synced is not None and TOMORROW_SUMMARY_PATH.exists():
|
| 847 |
+
return json.loads(TOMORROW_SUMMARY_PATH.read_text(encoding="utf-8"))
|
| 848 |
+
if TOMORROW_SUMMARY_PATH.exists():
|
| 849 |
+
return json.loads(TOMORROW_SUMMARY_PATH.read_text(encoding="utf-8"))
|
| 850 |
+
return {
|
| 851 |
+
"model_name": "nifty_tomorrow_direction_model",
|
| 852 |
+
"source_model": "locked_multiwindow_nifty50_ensemble",
|
| 853 |
+
"target": "next trading session NIFTY 50 direction",
|
| 854 |
+
"threshold": 0.54,
|
| 855 |
+
"validation_accuracy": 0.5673758865248227,
|
| 856 |
+
"test_accuracy": 0.6451612903225806,
|
| 857 |
+
"baseline_accuracy": 0.5053763440860215,
|
| 858 |
+
"n_test": 186,
|
| 859 |
+
"feature_count": 204,
|
| 860 |
+
}
|
| 861 |
+
|
| 862 |
+
|
| 863 |
+
def latest_tomorrow_prediction() -> dict[str, Any]:
|
| 864 |
+
sync_daily_forecaster_outputs()
|
| 865 |
+
latest_daily = latest_parquet_date(NIFTY_1D_PATH)
|
| 866 |
+
expected_daily = expected_completed_daily_date()
|
| 867 |
+
valid_daily = min(latest_daily, expected_daily) if latest_daily and expected_daily else (expected_daily or latest_daily)
|
| 868 |
+
|
| 869 |
+
if TOMORROW_LATEST_PATH.exists():
|
| 870 |
+
row = pd.read_csv(TOMORROW_LATEST_PATH).iloc[-1].to_dict()
|
| 871 |
+
cleaned = {k: (None if pd.isna(v) else v) for k, v in row.items()}
|
| 872 |
+
try:
|
| 873 |
+
input_day = date.fromisoformat(str(cleaned.get("input_date"))[:10])
|
| 874 |
+
except Exception:
|
| 875 |
+
input_day = None
|
| 876 |
+
if valid_daily is not None and (input_day is None or input_day < valid_daily):
|
| 877 |
+
try:
|
| 878 |
+
refreshed = refresh_tomorrow_prediction(session_date=valid_daily)
|
| 879 |
+
try:
|
| 880 |
+
refreshed_day = date.fromisoformat(str(refreshed.get("input_date"))[:10])
|
| 881 |
+
except Exception:
|
| 882 |
+
refreshed_day = None
|
| 883 |
+
if refreshed_day is not None and refreshed_day >= valid_daily:
|
| 884 |
+
return refreshed
|
| 885 |
+
except Exception:
|
| 886 |
+
pass
|
| 887 |
+
return cleaned
|
| 888 |
+
summary = load_tomorrow_summary()
|
| 889 |
+
try:
|
| 890 |
+
summary_input_day = date.fromisoformat(str(summary.get("latest_forecast_date"))[:10])
|
| 891 |
+
except Exception:
|
| 892 |
+
summary_input_day = None
|
| 893 |
+
if valid_daily is not None and (summary_input_day is None or summary_input_day < valid_daily):
|
| 894 |
+
try:
|
| 895 |
+
return refresh_tomorrow_prediction(session_date=valid_daily)
|
| 896 |
+
except Exception:
|
| 897 |
+
pass
|
| 898 |
+
return {
|
| 899 |
+
"input_date": summary.get("latest_forecast_date"),
|
| 900 |
+
"target_date": None,
|
| 901 |
"prediction": summary.get("latest_forecast_signal"),
|
| 902 |
"prob_up": summary.get("latest_forecast_prob_up"),
|
| 903 |
"confidence": None,
|
|
|
|
| 1053 |
return adjusted
|
| 1054 |
|
| 1055 |
|
| 1056 |
+
def refresh_tplus1_prediction(session_date: date | None = None) -> dict[str, Any]:
|
| 1057 |
+
if not TPLUS1_MODEL_PATH.exists():
|
| 1058 |
+
raise FileNotFoundError(f"Missing T+1 model artifact: {TPLUS1_MODEL_PATH}")
|
| 1059 |
+
payload = joblib.load(TPLUS1_MODEL_PATH)
|
| 1060 |
+
features = payload["features"]
|
| 1061 |
+
threshold = float(payload["threshold"])
|
| 1062 |
+
frame = _add_tplus1_target_features(_build_tplus1_session_features(_minute_frame_for_tplus1()))
|
| 1063 |
+
if session_date is not None:
|
| 1064 |
+
row = frame[pd.to_datetime(frame["date"], errors="coerce").dt.date == session_date].tail(1)
|
| 1065 |
+
else:
|
| 1066 |
+
row = frame.tail(1)
|
| 1067 |
+
if row.empty:
|
| 1068 |
+
minutes = fetch_yahoo_minutes(period="7d")
|
| 1069 |
+
append_parquet_rows(NIFTY_1M_PATH, minutes, ["date"])
|
| 1070 |
+
frame = _add_tplus1_target_features(_build_tplus1_session_features(_minute_frame_for_tplus1()))
|
| 1071 |
+
if session_date is not None:
|
| 1072 |
+
row = frame[pd.to_datetime(frame["date"], errors="coerce").dt.date == session_date].tail(1)
|
| 1073 |
+
else:
|
| 1074 |
+
row = frame.tail(1)
|
| 1075 |
+
if row.empty:
|
| 1076 |
+
raise RuntimeError("No complete 14:00-14:20 window is available for T+1 prediction.")
|
| 1077 |
missing = [col for col in features if col not in row.columns]
|
| 1078 |
if missing:
|
| 1079 |
raise RuntimeError(f"T+1 feature row is missing model features: {missing[:5]}")
|
|
|
|
| 1099 |
"validation_accuracy": summary.get("validation_accuracy"),
|
| 1100 |
"test_accuracy": summary.get("test_accuracy"),
|
| 1101 |
"accuracy_goal": summary.get("accuracy_goal"),
|
| 1102 |
+
"source": "live",
|
| 1103 |
}
|
| 1104 |
pd.DataFrame([out]).to_csv(TPLUS1_LATEST_PATH, index=False)
|
| 1105 |
+
_record_prediction_history(TPLUS1_PREDICTION_HISTORY_PATH, out, ["target_date"])
|
| 1106 |
clear_dashboard_payload_cache()
|
| 1107 |
return out
|
| 1108 |
|
|
|
|
| 1129 |
return float(np.clip(score, 0.35, 0.65))
|
| 1130 |
|
| 1131 |
|
| 1132 |
+
def refresh_tomorrow_prediction(session_date: date | None = None) -> dict[str, Any]:
|
| 1133 |
+
_archive_tomorrow_latest_to_history()
|
| 1134 |
+
synced = sync_daily_forecaster_outputs()
|
| 1135 |
+
if synced is not None and TOMORROW_LATEST_PATH.exists():
|
| 1136 |
+
latest = pd.read_csv(TOMORROW_LATEST_PATH).iloc[-1].to_dict()
|
| 1137 |
+
cleaned = {k: (None if pd.isna(v) else v) for k, v in latest.items()}
|
| 1138 |
+
cleaned["source"] = "live"
|
| 1139 |
+
_record_prediction_history(TOMORROW_PREDICTION_HISTORY_PATH, cleaned, ["target_date"])
|
| 1140 |
+
if session_date is None:
|
| 1141 |
+
clear_dashboard_payload_cache()
|
| 1142 |
+
return cleaned
|
| 1143 |
+
try:
|
| 1144 |
+
input_day = date.fromisoformat(str(cleaned.get("input_date"))[:10])
|
| 1145 |
+
except Exception:
|
| 1146 |
+
input_day = None
|
| 1147 |
+
if input_day is not None and (session_date is None or input_day >= session_date):
|
| 1148 |
+
clear_dashboard_payload_cache()
|
| 1149 |
+
return cleaned
|
| 1150 |
+
summary = load_tomorrow_summary()
|
| 1151 |
+
artifact = load_tomorrow_model_artifact()
|
| 1152 |
daily = pd.read_parquet(NIFTY_1D_PATH)
|
| 1153 |
daily["date"] = pd.to_datetime(daily["date"], errors="coerce").dt.normalize()
|
| 1154 |
daily = daily.dropna(subset=["date"]).sort_values("date")
|
|
|
|
| 1172 |
"source_model": str(summary.get("source_model", "tuned_daily_forest_single")),
|
| 1173 |
"validation_accuracy": float(summary.get("validation_accuracy", 0.5780141843971631)),
|
| 1174 |
"test_accuracy": float(summary.get("test_accuracy", 0.6182795698924731)),
|
| 1175 |
+
"source": "live",
|
| 1176 |
}
|
| 1177 |
pd.DataFrame([row]).to_csv(TOMORROW_LATEST_PATH, index=False)
|
| 1178 |
+
_record_prediction_history(TOMORROW_PREDICTION_HISTORY_PATH, row, ["target_date"])
|
| 1179 |
summary = dict(summary)
|
| 1180 |
+
summary.update(
|
| 1181 |
+
{
|
| 1182 |
+
"latest_forecast_date": row["input_date"],
|
| 1183 |
"latest_forecast_for": f"next trading session {row['target_date']}",
|
| 1184 |
"latest_forecast_prob_up": row["prob_up"],
|
| 1185 |
"latest_forecast_signal": row["prediction"],
|
| 1186 |
"latest_target_date": row["target_date"],
|
| 1187 |
+
}
|
| 1188 |
+
)
|
| 1189 |
+
TOMORROW_SUMMARY_PATH.write_text(json.dumps(summary, indent=2), encoding="utf-8")
|
| 1190 |
+
clear_dashboard_payload_cache()
|
| 1191 |
+
return row
|
| 1192 |
|
| 1193 |
|
| 1194 |
def _json_ready_frame(df: pd.DataFrame, limit: int | None = None) -> list[dict[str, Any]]:
|
|
|
|
| 1202 |
return out.to_dict(orient="records")
|
| 1203 |
|
| 1204 |
|
| 1205 |
+
|
| 1206 |
+
|
| 1207 |
def load_model_summary() -> dict[str, Any]:
|
| 1208 |
summary_path = MODEL_DIR / "summary.json"
|
| 1209 |
if not summary_path.exists():
|
|
|
|
| 1266 |
_file_cache_key(MODEL_DIR / "candidate_results.csv"),
|
| 1267 |
_file_cache_key(NIFTY_1M_PATH),
|
| 1268 |
_file_cache_key(LIVE_ACCURACY_PATH),
|
| 1269 |
+
_file_cache_key(TOMORROW_PREDICTION_HISTORY_PATH),
|
| 1270 |
)
|
| 1271 |
with _dashboard_payload_lock:
|
| 1272 |
return copy.deepcopy(_dashboard_payload_cached(key))
|
| 1273 |
|
| 1274 |
|
| 1275 |
+
def warm_dashboard_payload_cache() -> None:
|
| 1276 |
+
dashboard_payload()
|
| 1277 |
+
|
| 1278 |
+
|
| 1279 |
+
def _load_forecaster_predictions_by_target() -> dict[date, dict[str, Any]]:
|
| 1280 |
+
path = DAILY_FORECASTER_PREDICTIONS_PATH
|
| 1281 |
+
if not path.exists():
|
| 1282 |
+
return {}
|
| 1283 |
+
try:
|
| 1284 |
+
frame = pd.read_csv(path)
|
| 1285 |
+
except Exception:
|
| 1286 |
+
return {}
|
| 1287 |
+
if frame.empty:
|
| 1288 |
+
return {}
|
| 1289 |
+
if "symbol" in frame.columns:
|
| 1290 |
+
frame = frame[frame["symbol"].astype(str) == "NIFTY 50"].copy()
|
| 1291 |
+
indexed: dict[date, dict[str, Any]] = {}
|
| 1292 |
+
for _, row in frame.iterrows():
|
| 1293 |
+
target_day = _parse_iso_date(row.get("target_date"))
|
| 1294 |
+
if target_day is None:
|
| 1295 |
+
continue
|
| 1296 |
+
pred_value = row.get("pred")
|
| 1297 |
+
if pd.isna(pred_value) and "raw_pred" in row:
|
| 1298 |
+
pred_value = row.get("raw_pred")
|
| 1299 |
+
try:
|
| 1300 |
+
pred_int = int(pred_value)
|
| 1301 |
+
except Exception:
|
| 1302 |
+
continue
|
| 1303 |
+
prob_up = row.get("prob_up")
|
| 1304 |
+
try:
|
| 1305 |
+
prob_up = float(prob_up) if pd.notna(prob_up) else None
|
| 1306 |
+
except Exception:
|
| 1307 |
+
prob_up = None
|
| 1308 |
+
indexed[target_day] = {
|
| 1309 |
+
"prediction": "UP" if pred_int == 1 else "DOWN",
|
| 1310 |
+
"prob_up": prob_up,
|
| 1311 |
+
"forecast_date": row.get("forecast_date"),
|
| 1312 |
+
"source": "Tomorrow (forecaster)",
|
| 1313 |
+
}
|
| 1314 |
+
return indexed
|
| 1315 |
+
|
| 1316 |
+
|
| 1317 |
+
def _load_track_record_daily_rows() -> pd.DataFrame:
|
| 1318 |
+
frames: list[pd.DataFrame] = []
|
| 1319 |
+
if NIFTY_1D_PATH.exists():
|
| 1320 |
+
try:
|
| 1321 |
+
frames.append(pd.read_parquet(NIFTY_1D_PATH))
|
| 1322 |
+
except Exception:
|
| 1323 |
+
pass
|
| 1324 |
+
try:
|
| 1325 |
+
yahoo_daily = fetch_yahoo_daily(period="3mo")
|
| 1326 |
+
if not yahoo_daily.empty:
|
| 1327 |
+
frames.append(yahoo_daily)
|
| 1328 |
+
try:
|
| 1329 |
+
append_parquet_rows(NIFTY_1D_PATH, yahoo_daily, ["date"])
|
| 1330 |
+
except Exception:
|
| 1331 |
+
pass
|
| 1332 |
+
except Exception:
|
| 1333 |
+
pass
|
| 1334 |
+
|
| 1335 |
+
if not frames:
|
| 1336 |
+
return pd.DataFrame()
|
| 1337 |
+
|
| 1338 |
+
combined = pd.concat(frames, ignore_index=True)
|
| 1339 |
+
combined["date"] = pd.to_datetime(combined["date"], errors="coerce").dt.normalize()
|
| 1340 |
+
combined = combined.dropna(subset=["date"]).sort_values("date")
|
| 1341 |
+
combined = combined.drop_duplicates(subset=["date"], keep="last")
|
| 1342 |
+
combined = combined[
|
| 1343 |
+
combined["close"].map(lambda value: np.isfinite(float(value)) if pd.notna(value) else False)
|
| 1344 |
+
].copy()
|
| 1345 |
+
return combined.reset_index(drop=True)
|
| 1346 |
+
|
| 1347 |
+
|
| 1348 |
+
def _rolling_tomorrow_prediction(
|
| 1349 |
+
input_day: date,
|
| 1350 |
+
daily_rows: pd.DataFrame,
|
| 1351 |
+
threshold: float,
|
| 1352 |
+
fallback_prob: float,
|
| 1353 |
+
) -> tuple[str, float]:
|
| 1354 |
+
history = daily_rows[daily_rows["date"].dt.date <= input_day].copy()
|
| 1355 |
+
prob_up = _tomorrow_probability_from_daily(history, fallback_prob)
|
| 1356 |
+
prediction = "UP" if prob_up >= threshold else "DOWN"
|
| 1357 |
+
return prediction, float(prob_up)
|
| 1358 |
+
|
| 1359 |
+
|
| 1360 |
+
def build_prediction_track_record(
|
| 1361 |
+
sessions: int = 10,
|
| 1362 |
+
) -> list[dict[str, Any]]:
|
| 1363 |
+
summary = load_tomorrow_summary()
|
| 1364 |
+
artifact = load_tomorrow_model_artifact()
|
| 1365 |
+
threshold = float(artifact.get("threshold", summary.get("threshold", 0.534)))
|
| 1366 |
+
fallback_prob = float(summary.get("latest_forecast_prob_up", 0.49900560447008563))
|
| 1367 |
+
forecaster_by_target = _load_forecaster_predictions_by_target()
|
| 1368 |
+
|
| 1369 |
+
daily_rows = _load_track_record_daily_rows()
|
| 1370 |
+
if daily_rows.empty:
|
| 1371 |
+
return []
|
| 1372 |
+
|
| 1373 |
+
closes_by_date = {
|
| 1374 |
+
row["date"].date(): float(row["close"])
|
| 1375 |
+
for _, row in daily_rows.iterrows()
|
| 1376 |
+
if pd.notna(row["close"]) and np.isfinite(float(row["close"]))
|
| 1377 |
+
}
|
| 1378 |
+
|
| 1379 |
+
end_session = _track_record_end_session()
|
| 1380 |
+
available_through = max(
|
| 1381 |
+
(day for day in closes_by_date if day <= end_session),
|
| 1382 |
+
default=None,
|
| 1383 |
+
)
|
| 1384 |
+
if available_through is None:
|
| 1385 |
+
return []
|
| 1386 |
+
if available_through < end_session:
|
| 1387 |
+
end_session = available_through
|
| 1388 |
+
|
| 1389 |
+
session_dates = last_n_trading_sessions(end_session, sessions)
|
| 1390 |
+
|
| 1391 |
+
records: list[dict[str, Any]] = []
|
| 1392 |
+
for target_day in session_dates:
|
| 1393 |
+
day_close = closes_by_date.get(target_day)
|
| 1394 |
+
if day_close is None:
|
| 1395 |
+
continue
|
| 1396 |
+
actual_move, actual_direction = _tomorrow_actual_outcome(target_day, day_close, closes_by_date)
|
| 1397 |
+
if actual_direction is None:
|
| 1398 |
+
continue
|
| 1399 |
+
|
| 1400 |
+
input_day = previous_trading_day(target_day - timedelta(days=1))
|
| 1401 |
+
cached = forecaster_by_target.get(target_day)
|
| 1402 |
+
if cached and cached.get("prediction") in {"UP", "DOWN"}:
|
| 1403 |
+
prediction = cached["prediction"]
|
| 1404 |
+
prob_up = cached.get("prob_up")
|
| 1405 |
+
source = cached.get("source", "Tomorrow (forecaster)")
|
| 1406 |
+
else:
|
| 1407 |
+
prediction, prob_up = _rolling_tomorrow_prediction(
|
| 1408 |
+
input_day,
|
| 1409 |
+
daily_rows,
|
| 1410 |
+
threshold,
|
| 1411 |
+
fallback_prob,
|
| 1412 |
+
)
|
| 1413 |
+
source = "Tomorrow (rolling)"
|
| 1414 |
+
|
| 1415 |
+
if prediction not in {"UP", "DOWN"}:
|
| 1416 |
+
continue
|
| 1417 |
+
|
| 1418 |
+
records.append(
|
| 1419 |
+
{
|
| 1420 |
+
"date": target_day.isoformat(),
|
| 1421 |
+
"input_date": input_day.isoformat(),
|
| 1422 |
+
"prediction": prediction,
|
| 1423 |
+
"prediction_source": source,
|
| 1424 |
+
"prob_up": prob_up,
|
| 1425 |
+
"actual_move": actual_move,
|
| 1426 |
+
"actual_direction": actual_direction,
|
| 1427 |
+
"correct": prediction == actual_direction,
|
| 1428 |
+
}
|
| 1429 |
+
)
|
| 1430 |
+
return records[-sessions:]
|
| 1431 |
+
|
| 1432 |
+
|
| 1433 |
+
@lru_cache(maxsize=4)
|
| 1434 |
+
def _dashboard_payload_cached(key: tuple[tuple[str, int | None, int | None], ...]) -> dict[str, Any]:
|
| 1435 |
summary = load_model_summary()
|
| 1436 |
t5_latest = _latest_saved_prediction_uncached()
|
| 1437 |
tomorrow_summary = load_tomorrow_summary()
|
| 1438 |
tomorrow_latest = latest_tomorrow_prediction()
|
| 1439 |
tplus1_summary = load_tplus1_summary()
|
| 1440 |
tplus1_latest = latest_tplus1_prediction()
|
|
|
|
| 1441 |
t5_test = load_test_predictions()
|
| 1442 |
tomorrow_test = load_tomorrow_test_predictions()
|
| 1443 |
+
tomorrow_history = _load_prediction_history(TOMORROW_PREDICTION_HISTORY_PATH)
|
| 1444 |
tplus1_test = load_tplus1_test_predictions()
|
| 1445 |
daily = pd.read_parquet(NIFTY_1D_PATH)
|
| 1446 |
daily["date"] = pd.to_datetime(daily["date"], errors="coerce")
|
| 1447 |
daily = daily.sort_values("date").tail(180)
|
|
|
|
|
|
|
| 1448 |
|
| 1449 |
if not t5_test.empty:
|
| 1450 |
+
recent_accuracy = float(t5_test.tail(40)["correct"].mean())
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1451 |
else:
|
|
|
|
| 1452 |
recent_accuracy = None
|
|
|
|
|
|
|
| 1453 |
|
| 1454 |
if not tomorrow_test.empty:
|
| 1455 |
tomorrow_recent = tomorrow_test.tail(40).copy()
|
|
|
|
| 1459 |
tomorrow_recent["correct"] = pd.to_numeric(tomorrow_recent["target"], errors="coerce") == pd.to_numeric(tomorrow_recent["pred"], errors="coerce")
|
| 1460 |
tomorrow_accuracy = float(tomorrow_recent["correct"].mean()) if "correct" in tomorrow_recent.columns else tomorrow_summary.get("test_accuracy")
|
| 1461 |
else:
|
|
|
|
| 1462 |
tomorrow_accuracy = tomorrow_summary.get("test_accuracy")
|
| 1463 |
|
| 1464 |
model_metrics = [
|
|
|
|
| 1493 |
"test_rows": int(len(t5_test)) if not t5_test.empty else int(summary.get("test_rows") or 0),
|
| 1494 |
},
|
| 1495 |
]
|
| 1496 |
+
metrics = {
|
| 1497 |
+
"validation_accuracy": tomorrow_summary.get("validation_accuracy"),
|
| 1498 |
+
"test_accuracy": tomorrow_summary.get("test_accuracy"),
|
| 1499 |
"baseline_test_accuracy": tomorrow_summary.get("baseline_accuracy"),
|
| 1500 |
"validation_auc": summary.get("validation_auc"),
|
| 1501 |
"test_auc": summary.get("test_auc"),
|
| 1502 |
"test_brier": summary.get("test_brier"),
|
| 1503 |
"feature_count": tomorrow_summary.get("feature_count"),
|
| 1504 |
"recent_accuracy": tomorrow_accuracy,
|
| 1505 |
+
"recent_accuracy_days": int(len(tomorrow_test.tail(40))) if not tomorrow_test.empty else 0,
|
| 1506 |
+
"total_test_days": int(tomorrow_summary.get("n_test") or len(tomorrow_test) or 0),
|
| 1507 |
+
"models": model_metrics,
|
| 1508 |
+
}
|
| 1509 |
+
return {
|
| 1510 |
+
"timestamp": datetime.now(ZoneInfo("Asia/Kolkata")).isoformat(),
|
| 1511 |
+
"predictions": {
|
| 1512 |
+
"t5": {
|
| 1513 |
+
"latest": t5_latest,
|
| 1514 |
+
"summary": summary,
|
| 1515 |
+
},
|
| 1516 |
+
"tomorrow": {
|
| 1517 |
+
"latest": tomorrow_latest,
|
| 1518 |
+
"summary": tomorrow_summary,
|
| 1519 |
+
},
|
| 1520 |
+
"tplus1": {
|
| 1521 |
+
"latest": tplus1_latest,
|
| 1522 |
+
"summary": tplus1_summary,
|
| 1523 |
+
},
|
| 1524 |
+
},
|
| 1525 |
"metrics": metrics,
|
| 1526 |
+
"models": model_metrics,
|
| 1527 |
+
"live_accuracy": load_live_accuracy(),
|
|
|
|
|
|
|
| 1528 |
"charts": {
|
| 1529 |
+
"daily_closes": _json_ready_frame(daily[["date", "close"]]),
|
| 1530 |
+
"t5_backtest": _json_ready_frame(t5_test, limit=400),
|
| 1531 |
+
"t5_recent_predictions": _json_ready_frame(t5_test.tail(40)),
|
| 1532 |
+
"tomorrow_backtest": _json_ready_frame(tomorrow_test, limit=400),
|
| 1533 |
+
"tomorrow_live_track_record": build_prediction_track_record(),
|
| 1534 |
+
"tomorrow_history_predictions": _json_ready_frame(tomorrow_history.tail(80)),
|
| 1535 |
+
"tplus1_backtest": _json_ready_frame(tplus1_test, limit=400),
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1536 |
},
|
| 1537 |
}
|
| 1538 |
|
|
|
|
| 1551 |
merged = merged.drop_duplicates(subset=["date"], keep="last").sort_values("date").reset_index(drop=True)
|
| 1552 |
merged.to_parquet(OPENING_DATASET_PATH, index=False, compression="zstd")
|
| 1553 |
prediction = predict_row(row)
|
|
|
|
| 1554 |
return prediction
|
| 1555 |
|
| 1556 |
|
| 1557 |
def refresh_daily_data() -> dict[str, Any]:
|
| 1558 |
daily = fetch_yahoo_daily(period="1mo")
|
| 1559 |
combined = append_parquet_rows(NIFTY_1D_PATH, daily, ["date"])
|
|
|
|
| 1560 |
return {
|
| 1561 |
"rows": int(len(combined)),
|
| 1562 |
"latest_date": pd.to_datetime(combined["date"]).max().date().isoformat(),
|
|
|
|
| 1609 |
dataset = dataset.drop(columns=["_session_date"])
|
| 1610 |
dataset = dataset.sort_values("date").reset_index(drop=True)
|
| 1611 |
dataset.to_parquet(OPENING_DATASET_PATH, index=False, compression="zstd")
|
|
|
|
| 1612 |
latest = pd.to_datetime(dataset["date"], errors="coerce").max()
|
| 1613 |
return {
|
| 1614 |
"updated_rows": int(updated),
|
|
|
|
| 1616 |
}
|
| 1617 |
|
| 1618 |
|
| 1619 |
+
def load_live_accuracy() -> dict[str, Any]:
|
| 1620 |
+
"""Load the live accuracy ledger from disk."""
|
| 1621 |
+
default = {
|
| 1622 |
+
"tomorrow": {"entries": [], "accuracy": None, "total": 0, "correct_count": 0, "backtest_count": 0, "live_count": 0},
|
| 1623 |
+
"t5": {"entries": [], "accuracy": None, "total": 0, "correct_count": 0, "backtest_count": 0, "live_count": 0},
|
| 1624 |
+
"tplus1": {"entries": [], "accuracy": None, "total": 0, "correct_count": 0, "backtest_count": 0, "live_count": 0},
|
| 1625 |
+
}
|
| 1626 |
+
|
| 1627 |
+
if LIVE_ACCURACY_PATH.exists():
|
| 1628 |
+
try:
|
| 1629 |
+
raw = json.loads(LIVE_ACCURACY_PATH.read_text(encoding="utf-8"))
|
| 1630 |
+
except Exception:
|
| 1631 |
+
raw = None
|
| 1632 |
+
if isinstance(raw, dict):
|
| 1633 |
+
try:
|
| 1634 |
+
for model_id in default:
|
| 1635 |
+
current = raw.get(model_id, {})
|
| 1636 |
+
if not isinstance(current, dict):
|
| 1637 |
+
current = {}
|
| 1638 |
+
entries = current.get("entries", [])
|
| 1639 |
+
if not isinstance(entries, list):
|
| 1640 |
+
entries = []
|
| 1641 |
+
backtest_entries = [entry for entry in entries if str(entry.get("source", "backtest")).lower() == "backtest"]
|
| 1642 |
+
live_entries = [entry for entry in entries if str(entry.get("source", "backtest")).lower() != "backtest"]
|
| 1643 |
+
total = len(entries)
|
| 1644 |
+
correct = sum(1 for e in entries if e.get("correct"))
|
| 1645 |
+
current["entries"] = entries
|
| 1646 |
+
current["backtest_count"] = int(len(backtest_entries))
|
| 1647 |
+
current["live_count"] = int(len(live_entries))
|
| 1648 |
+
current["total"] = int(total)
|
| 1649 |
+
current["correct_count"] = int(correct)
|
| 1650 |
+
current["accuracy"] = (current["correct_count"] / current["total"]) if current["total"] > 0 else None
|
| 1651 |
+
default[model_id].update(current)
|
| 1652 |
+
return default
|
| 1653 |
+
except Exception:
|
| 1654 |
+
pass
|
| 1655 |
+
return default
|
| 1656 |
+
|
| 1657 |
+
|
| 1658 |
+
def save_live_accuracy(data: dict[str, Any]) -> None:
|
| 1659 |
+
"""Persist the live accuracy ledger to disk."""
|
| 1660 |
+
LIVE_ACCURACY_PATH.write_text(json.dumps(data, indent=2), encoding="utf-8")
|
| 1661 |
+
|
| 1662 |
+
|
| 1663 |
+
def _load_prediction_history(path: Path) -> pd.DataFrame:
|
| 1664 |
+
if not path.exists():
|
| 1665 |
+
return pd.DataFrame()
|
| 1666 |
+
frame = pd.read_parquet(path)
|
| 1667 |
+
for col in ("date", "input_date", "target_date", "forecast_date"):
|
| 1668 |
+
if col in frame.columns:
|
| 1669 |
+
frame[col] = pd.to_datetime(frame[col], errors="coerce")
|
| 1670 |
+
sort_cols = [col for col in ("target_date", "input_date", "date", "forecast_date") if col in frame.columns]
|
| 1671 |
+
if sort_cols:
|
| 1672 |
+
return frame.sort_values(sort_cols).reset_index(drop=True)
|
| 1673 |
+
return frame.reset_index(drop=True)
|
| 1674 |
+
|
| 1675 |
+
|
| 1676 |
+
def _record_prediction_history(path: Path, row: dict[str, Any], subset: list[str]) -> None:
|
| 1677 |
+
append_prediction_history(path, row, subset)
|
| 1678 |
+
|
| 1679 |
+
|
| 1680 |
+
def _rescore_tomorrow_live_ledger(ledger: dict[str, Any]) -> bool:
|
| 1681 |
+
"""Fix live Tomorrow ledger entries to use close vs previous close. Returns True if modified."""
|
| 1682 |
+
daily = pd.read_parquet(NIFTY_1D_PATH)
|
| 1683 |
+
daily["_date"] = pd.to_datetime(daily["date"], errors="coerce").dt.normalize()
|
| 1684 |
+
closes_by_date: dict[date, float] = {}
|
| 1685 |
+
for _, row in daily.iterrows():
|
| 1686 |
+
if pd.isna(row["_date"]):
|
| 1687 |
+
continue
|
| 1688 |
+
close = row.get("close")
|
| 1689 |
+
if pd.notna(close) and np.isfinite(float(close)):
|
| 1690 |
+
closes_by_date[row["_date"].date()] = float(close)
|
| 1691 |
+
|
| 1692 |
+
changed = False
|
| 1693 |
+
for entry in ledger.get("tomorrow", {}).get("entries", []):
|
| 1694 |
+
if str(entry.get("source", "backtest")).lower() == "backtest":
|
| 1695 |
+
continue
|
| 1696 |
+
try:
|
| 1697 |
+
day = date.fromisoformat(str(entry.get("date", ""))[:10])
|
| 1698 |
+
except Exception:
|
| 1699 |
+
continue
|
| 1700 |
+
day_close = closes_by_date.get(day)
|
| 1701 |
+
if day_close is None:
|
| 1702 |
+
continue
|
| 1703 |
+
_, actual_direction = _tomorrow_actual_outcome(day, day_close, closes_by_date)
|
| 1704 |
+
if actual_direction is None:
|
| 1705 |
+
continue
|
| 1706 |
+
pred = str(entry.get("prediction", "")).upper()
|
| 1707 |
+
if pred not in {"UP", "DOWN"}:
|
| 1708 |
+
continue
|
| 1709 |
+
new_correct = pred == actual_direction
|
| 1710 |
+
if entry.get("actual") != actual_direction or entry.get("correct") != new_correct:
|
| 1711 |
+
entry["actual"] = actual_direction
|
| 1712 |
+
entry["correct"] = new_correct
|
| 1713 |
+
changed = True
|
| 1714 |
+
return changed
|
| 1715 |
+
|
| 1716 |
+
|
| 1717 |
+
def ensure_completed_sessions_scored(
|
| 1718 |
+
now: datetime | None = None,
|
| 1719 |
+
ledger: dict[str, Any] | None = None,
|
| 1720 |
+
) -> dict[str, Any]:
|
| 1721 |
+
"""Score any completed Tomorrow sessions that have daily close data but no ledger entry."""
|
| 1722 |
+
now = now or datetime.now(IST)
|
| 1723 |
+
completed = expected_completed_daily_date(now)
|
| 1724 |
+
if not is_trading_day(completed):
|
| 1725 |
+
return ledger or load_live_accuracy()
|
| 1726 |
+
|
| 1727 |
+
ledger = ledger or load_live_accuracy()
|
| 1728 |
+
if _rescore_tomorrow_live_ledger(ledger):
|
| 1729 |
+
for model_id in ("tomorrow",):
|
| 1730 |
+
entries = ledger[model_id]["entries"]
|
| 1731 |
+
total = len(entries)
|
| 1732 |
+
correct = sum(1 for e in entries if e.get("correct"))
|
| 1733 |
+
backtest_count = sum(1 for e in entries if str(e.get("source", "backtest")).lower() == "backtest")
|
| 1734 |
+
ledger[model_id]["total"] = total
|
| 1735 |
+
ledger[model_id]["correct_count"] = correct
|
| 1736 |
+
ledger[model_id]["backtest_count"] = backtest_count
|
| 1737 |
+
ledger[model_id]["live_count"] = total - backtest_count
|
| 1738 |
+
ledger[model_id]["accuracy"] = correct / total if total > 0 else None
|
| 1739 |
+
save_live_accuracy(ledger)
|
| 1740 |
+
logged_tom = {e["date"] for e in ledger.get("tomorrow", {}).get("entries", [])}
|
| 1741 |
+
if completed.isoformat() in logged_tom:
|
| 1742 |
+
return ledger
|
| 1743 |
+
|
| 1744 |
+
daily = pd.read_parquet(NIFTY_1D_PATH)
|
| 1745 |
+
daily["_date"] = pd.to_datetime(daily["date"], errors="coerce").dt.normalize()
|
| 1746 |
+
day_rows = daily[daily["_date"].dt.date == completed]
|
| 1747 |
+
if day_rows.empty:
|
| 1748 |
+
return ledger
|
| 1749 |
+
|
| 1750 |
+
day_open = float(day_rows.iloc[-1]["open"])
|
| 1751 |
+
day_close = float(day_rows.iloc[-1]["close"])
|
| 1752 |
+
if not (np.isfinite(day_open) and np.isfinite(day_close) and day_open != 0):
|
| 1753 |
+
return ledger
|
| 1754 |
+
|
| 1755 |
+
return update_live_accuracy(completed)
|
| 1756 |
+
|
| 1757 |
+
|
| 1758 |
+
def update_live_accuracy(session_date: date) -> dict[str, Any]:
|
| 1759 |
+
"""Score today's predictions against actual outcomes and update the ledger.
|
| 1760 |
+
|
| 1761 |
+
Must be called AFTER refresh_daily_data() (so today's close is available)
|
| 1762 |
+
but BEFORE refresh_first5_prediction / refresh_tplus1_prediction /
|
| 1763 |
+
refresh_tomorrow_prediction (so the CSV files still hold the predictions
|
| 1764 |
+
we want to score).
|
| 1765 |
+
"""
|
| 1766 |
+
ledger = load_live_accuracy()
|
| 1767 |
+
daily = pd.read_parquet(NIFTY_1D_PATH)
|
| 1768 |
+
daily["_date"] = pd.to_datetime(daily["date"], errors="coerce").dt.normalize()
|
| 1769 |
+
today_rows = daily[daily["_date"].dt.date == session_date]
|
| 1770 |
+
if today_rows.empty:
|
| 1771 |
+
return ledger
|
| 1772 |
+
|
| 1773 |
+
day_open = float(today_rows.iloc[-1]["open"])
|
| 1774 |
+
day_close = float(today_rows.iloc[-1]["close"])
|
| 1775 |
+
if not (np.isfinite(day_open) and np.isfinite(day_close) and day_open != 0):
|
| 1776 |
+
return ledger
|
| 1777 |
+
actual_close_gt_open = "UP" if day_close > day_open else "DOWN"
|
| 1778 |
+
session_iso = session_date.isoformat()
|
| 1779 |
+
|
| 1780 |
+
# --- T+5: today's 9:20 AM prediction vs close > open ---
|
| 1781 |
+
logged_t5 = {e["date"] for e in ledger["t5"]["entries"]}
|
| 1782 |
+
if session_iso not in logged_t5:
|
| 1783 |
+
t5_history = _load_prediction_history(T5_PREDICTION_HISTORY_PATH)
|
| 1784 |
+
if not t5_history.empty and "target_date" in t5_history.columns:
|
| 1785 |
+
t5_rows = t5_history[t5_history["target_date"].dt.date == session_date]
|
| 1786 |
+
else:
|
| 1787 |
+
t5_rows = pd.DataFrame()
|
| 1788 |
+
if t5_rows.empty and LATEST_PATH.exists():
|
| 1789 |
+
try:
|
| 1790 |
+
t5_row = pd.read_csv(LATEST_PATH).iloc[-1].to_dict()
|
| 1791 |
+
if str(t5_row.get("input_date", ""))[:10] == session_iso:
|
| 1792 |
+
t5_rows = pd.DataFrame([t5_row])
|
| 1793 |
+
except Exception:
|
| 1794 |
+
t5_rows = pd.DataFrame()
|
| 1795 |
+
if not t5_rows.empty:
|
| 1796 |
+
try:
|
| 1797 |
+
t5_row = t5_rows.iloc[-1].to_dict()
|
| 1798 |
+
pred = str(t5_row.get("prediction", "")).upper()
|
| 1799 |
+
if pred in ("UP", "DOWN"):
|
| 1800 |
+
ledger["t5"]["entries"].append({
|
| 1801 |
+
"date": session_iso,
|
| 1802 |
+
"prediction": pred,
|
| 1803 |
+
"actual": actual_close_gt_open,
|
| 1804 |
+
"correct": pred == actual_close_gt_open,
|
| 1805 |
+
"source": "live",
|
| 1806 |
+
})
|
| 1807 |
+
except Exception:
|
| 1808 |
+
pass
|
| 1809 |
+
|
| 1810 |
+
# --- Tomorrow: prior close vs today's close (matches forecaster target) ---
|
| 1811 |
+
logged_tom = {e["date"] for e in ledger["tomorrow"]["entries"]}
|
| 1812 |
+
if session_iso not in logged_tom:
|
| 1813 |
+
prev_day = previous_trading_day(session_date - timedelta(days=1))
|
| 1814 |
+
prev_rows = daily[daily["_date"].dt.date == prev_day]
|
| 1815 |
+
actual_tomorrow = None
|
| 1816 |
+
if not prev_rows.empty:
|
| 1817 |
+
prev_close = float(prev_rows.iloc[-1]["close"])
|
| 1818 |
+
if np.isfinite(prev_close) and prev_close != 0:
|
| 1819 |
+
actual_tomorrow = "UP" if day_close > prev_close else "DOWN"
|
| 1820 |
+
tom_row = _find_tomorrow_prediction_for_target(session_date)
|
| 1821 |
+
if tom_row and actual_tomorrow is not None:
|
| 1822 |
+
try:
|
| 1823 |
+
pred = str(tom_row.get("prediction", "")).upper()
|
| 1824 |
+
if pred in ("UP", "DOWN"):
|
| 1825 |
+
ledger["tomorrow"]["entries"].append({
|
| 1826 |
+
"date": session_iso,
|
| 1827 |
+
"prediction": pred,
|
| 1828 |
+
"actual": actual_tomorrow,
|
| 1829 |
+
"correct": pred == actual_tomorrow,
|
| 1830 |
+
"source": "live",
|
| 1831 |
+
})
|
| 1832 |
+
except Exception:
|
| 1833 |
+
pass
|
| 1834 |
+
|
| 1835 |
+
# --- T+1: yesterday's 14:20 prediction targeting today ---
|
| 1836 |
+
# T+1 target: today's close > yesterday's 14:20 close
|
| 1837 |
+
logged_t1 = {e["date"] for e in ledger["tplus1"]["entries"]}
|
| 1838 |
+
if session_iso not in logged_t1:
|
| 1839 |
+
t1_history = _load_prediction_history(TPLUS1_PREDICTION_HISTORY_PATH)
|
| 1840 |
+
if not t1_history.empty and "target_date" in t1_history.columns:
|
| 1841 |
+
t1_rows = t1_history[t1_history["target_date"].dt.date == session_date]
|
| 1842 |
+
else:
|
| 1843 |
+
t1_rows = pd.DataFrame()
|
| 1844 |
+
if not t1_rows.empty:
|
| 1845 |
+
try:
|
| 1846 |
+
t1_row = t1_rows.iloc[-1].to_dict()
|
| 1847 |
+
pred = str(t1_row.get("prediction", "")).upper()
|
| 1848 |
+
input_date_str = str(t1_row.get("input_date", ""))[:10]
|
| 1849 |
+
input_day = date.fromisoformat(input_date_str)
|
| 1850 |
+
# Read the 14:20 close from minute data for the input session
|
| 1851 |
+
minute = pd.read_parquet(NIFTY_1M_PATH, columns=["date", "close"])
|
| 1852 |
+
minute["dt"] = pd.to_datetime(minute["date"], errors="coerce")
|
| 1853 |
+
minute = minute.dropna(subset=["dt"])
|
| 1854 |
+
minute["session_date"] = minute["dt"].dt.normalize()
|
| 1855 |
+
minute["time_str"] = minute["dt"].dt.strftime("%H:%M")
|
| 1856 |
+
window = minute[
|
| 1857 |
+
(minute["session_date"].dt.date == input_day)
|
| 1858 |
+
& (minute["time_str"] >= "14:00")
|
| 1859 |
+
& (minute["time_str"] <= "14:20")
|
| 1860 |
+
].sort_values("dt")
|
| 1861 |
+
if not window.empty and pred in ("UP", "DOWN"):
|
| 1862 |
+
w_close = float(window.iloc[-1]["close"])
|
| 1863 |
+
t1_actual = "UP" if day_close > w_close else "DOWN"
|
| 1864 |
+
ledger["tplus1"]["entries"].append({
|
| 1865 |
+
"date": session_iso,
|
| 1866 |
+
"prediction": pred,
|
| 1867 |
+
"actual": t1_actual,
|
| 1868 |
+
"correct": pred == t1_actual,
|
| 1869 |
+
"source": "live",
|
| 1870 |
+
})
|
| 1871 |
+
except Exception:
|
| 1872 |
+
pass
|
| 1873 |
+
|
| 1874 |
+
_rescore_tomorrow_live_ledger(ledger)
|
| 1875 |
+
|
| 1876 |
+
# Recompute summary stats
|
| 1877 |
+
for model_id in ("t5", "tomorrow", "tplus1"):
|
| 1878 |
+
entries = ledger[model_id]["entries"]
|
| 1879 |
+
total = len(entries)
|
| 1880 |
+
correct = sum(1 for e in entries if e.get("correct"))
|
| 1881 |
+
backtest_count = sum(1 for e in entries if str(e.get("source", "backtest")).lower() == "backtest")
|
| 1882 |
+
ledger[model_id]["total"] = total
|
| 1883 |
+
ledger[model_id]["correct_count"] = correct
|
| 1884 |
+
ledger[model_id]["backtest_count"] = backtest_count
|
| 1885 |
+
ledger[model_id]["live_count"] = total - backtest_count
|
| 1886 |
+
ledger[model_id]["accuracy"] = correct / total if total > 0 else None
|
| 1887 |
+
|
| 1888 |
+
save_live_accuracy(ledger)
|
| 1889 |
+
return ledger
|
| 1890 |
+
|
| 1891 |
+
|
| 1892 |
def refresh_market_close_data(session_date: date | None = None) -> dict[str, Any]:
|
| 1893 |
now = datetime.now(IST)
|
| 1894 |
session_date = session_date or now.date()
|
| 1895 |
if not is_trading_day(session_date):
|
| 1896 |
raise RuntimeError(f"{session_date.isoformat()} is not an NSE trading session.")
|
|
|
|
| 1897 |
try:
|
|
|
|
| 1898 |
minutes = fetch_yahoo_minutes(period="7d")
|
| 1899 |
minute_frame = append_parquet_rows(NIFTY_1M_PATH, minutes, ["date"])
|
| 1900 |
daily_info = refresh_daily_data()
|
|
|
|
| 1907 |
tplus1_prediction = refresh_tplus1_prediction(session_date=session_date)
|
| 1908 |
outcomes = update_opening_outcomes_from_daily()
|
| 1909 |
tomorrow_prediction = refresh_tomorrow_prediction(session_date=session_date)
|
|
|
|
|
|
|
| 1910 |
return {
|
| 1911 |
"session_date": session_date.isoformat(),
|
| 1912 |
"nifty_1m_rows": int(len(minute_frame)),
|
|
|
|
| 1916 |
"t5_prediction": t5_prediction.to_dict(),
|
| 1917 |
"tplus1_prediction": tplus1_prediction,
|
| 1918 |
"tomorrow_prediction": tomorrow_prediction,
|
|
|
|
| 1919 |
}
|
| 1920 |
+
except Exception:
|
|
|
|
|
|
|
| 1921 |
raise
|
| 1922 |
|
| 1923 |
|
| 1924 |
+
def close_refresh_due(now: datetime | None = None) -> bool:
|
| 1925 |
now = now or datetime.now(IST)
|
| 1926 |
if not is_trading_day(now.date()) or now.time() < CLOSE_REFRESH_READY:
|
| 1927 |
return False
|
|
|
|
| 1936 |
tomorrow_input = date.fromisoformat(str(tomorrow_latest.get("input_date"))[:10])
|
| 1937 |
except Exception:
|
| 1938 |
tomorrow_input = None
|
| 1939 |
+
return any(
|
| 1940 |
+
latest != now.date()
|
| 1941 |
+
for latest in (latest_daily, latest_minutes, latest_opening, latest_opening_outcome, tomorrow_input)
|
| 1942 |
+
)
|
| 1943 |
+
|
| 1944 |
+
|
| 1945 |
+
def latest_prediction_input_date(path: Path) -> date | None:
|
| 1946 |
+
if not path.exists():
|
| 1947 |
+
return None
|
| 1948 |
+
try:
|
| 1949 |
+
frame = pd.read_csv(path, usecols=["input_date"])
|
| 1950 |
+
except Exception:
|
| 1951 |
+
return None
|
| 1952 |
+
if frame.empty:
|
| 1953 |
+
return None
|
| 1954 |
+
value = pd.to_datetime(frame["input_date"], errors="coerce").max()
|
| 1955 |
+
return None if pd.isna(value) else value.date()
|
| 1956 |
+
|
| 1957 |
+
|
| 1958 |
+
def latest_tomorrow_input_date() -> date | None:
|
| 1959 |
+
try:
|
| 1960 |
+
latest = latest_tomorrow_prediction()
|
| 1961 |
+
raw = latest.get("input_date")
|
| 1962 |
+
return date.fromisoformat(str(raw)[:10]) if raw else None
|
| 1963 |
+
except Exception:
|
| 1964 |
+
return None
|
| 1965 |
+
|
| 1966 |
+
|
| 1967 |
+
def expected_completed_daily_date(now: datetime | None = None) -> date:
|
| 1968 |
+
now = now or datetime.now(IST)
|
| 1969 |
+
if is_trading_day(now.date()) and now.time() < CLOSE_REFRESH_READY:
|
| 1970 |
+
return previous_trading_day(now.date() - timedelta(days=1))
|
| 1971 |
+
return previous_trading_day(now.date())
|
| 1972 |
+
|
| 1973 |
+
|
| 1974 |
+
def expected_minute_date(now: datetime | None = None) -> date:
|
| 1975 |
+
now = now or datetime.now(IST)
|
| 1976 |
+
if is_trading_day(now.date()) and now.time() >= FIRST5_READY:
|
| 1977 |
+
return now.date()
|
| 1978 |
+
return previous_trading_day(now.date() - timedelta(days=1))
|
| 1979 |
+
|
| 1980 |
+
|
| 1981 |
+
def expected_tplus1_date(now: datetime | None = None) -> date:
|
| 1982 |
+
now = now or datetime.now(IST)
|
| 1983 |
+
if is_trading_day(now.date()) and now.time() >= TPLUS1_READY:
|
| 1984 |
+
return now.date()
|
| 1985 |
+
return previous_trading_day(now.date() - timedelta(days=1))
|
| 1986 |
+
|
| 1987 |
+
|
| 1988 |
+
def is_stale(latest: date | None, expected: date) -> bool:
|
| 1989 |
+
return latest is None or latest < expected
|
| 1990 |
+
|
| 1991 |
+
|
| 1992 |
+
def stale_data_status(now: datetime | None = None) -> dict[str, Any]:
|
| 1993 |
+
now = now or datetime.now(IST)
|
| 1994 |
+
expected_daily = expected_completed_daily_date(now)
|
| 1995 |
+
expected_minutes = expected_minute_date(now)
|
| 1996 |
+
expected_tplus1 = expected_tplus1_date(now)
|
| 1997 |
+
latest_1d = latest_parquet_date(NIFTY_1D_PATH)
|
| 1998 |
+
latest_1m = latest_parquet_date(NIFTY_1M_PATH)
|
| 1999 |
+
latest_t5 = latest_prediction_input_date(LATEST_PATH)
|
| 2000 |
+
latest_tomorrow = latest_tomorrow_input_date()
|
| 2001 |
+
latest_tplus1 = latest_prediction_input_date(TPLUS1_LATEST_PATH)
|
| 2002 |
+
return {
|
| 2003 |
+
"daily_stale": expected_daily > (latest_1d or date.min),
|
| 2004 |
+
"minutes_stale": expected_minutes > (latest_1m or date.min),
|
| 2005 |
+
"t5_stale": is_stale(latest_t5, expected_minutes),
|
| 2006 |
+
"tomorrow_stale": is_stale(latest_tomorrow, expected_daily),
|
| 2007 |
+
"tplus1_stale": is_stale(latest_tplus1, expected_tplus1),
|
| 2008 |
+
}
|
| 2009 |
+
|
| 2010 |
+
|
| 2011 |
+
def refresh_stale_data_once(now: datetime | None = None) -> dict[str, Any]:
|
| 2012 |
+
now = now or datetime.now(IST)
|
| 2013 |
+
status = stale_data_status(now)
|
| 2014 |
+
if not any(status.values()):
|
| 2015 |
+
return {"status": "fresh", "actions": []}
|
| 2016 |
+
if not _stale_refresh_lock.acquire(blocking=False):
|
| 2017 |
+
return {"status": "skipped", "reason": "stale refresh already running", **status, "actions": []}
|
| 2018 |
+
|
| 2019 |
+
actions: list[dict[str, Any]] = []
|
| 2020 |
+
try:
|
| 2021 |
+
if status["minutes_stale"]:
|
| 2022 |
+
minutes = fetch_yahoo_minutes(period="7d")
|
| 2023 |
+
combined = append_parquet_rows(NIFTY_1M_PATH, minutes, ["date"])
|
| 2024 |
+
actions.append(
|
| 2025 |
+
{
|
| 2026 |
+
"name": "minutes",
|
| 2027 |
+
"rows": int(len(combined)),
|
| 2028 |
+
"latest_date": pd.to_datetime(combined["date"], errors="coerce").max().date().isoformat(),
|
| 2029 |
+
}
|
| 2030 |
+
)
|
| 2031 |
+
|
| 2032 |
+
if status["daily_stale"]:
|
| 2033 |
+
daily_info = refresh_daily_data()
|
| 2034 |
+
outcomes = update_opening_outcomes_from_daily()
|
| 2035 |
+
actions.append({"name": "daily", **daily_info})
|
| 2036 |
+
actions.append({"name": "opening_outcomes", **outcomes})
|
| 2037 |
+
try:
|
| 2038 |
+
completed = date.fromisoformat(status["expected_daily_date"])
|
| 2039 |
+
scored = update_live_accuracy(completed)
|
| 2040 |
+
actions.append(
|
| 2041 |
+
{
|
| 2042 |
+
"name": "tomorrow_live_accuracy",
|
| 2043 |
+
"session_date": completed.isoformat(),
|
| 2044 |
+
"live_count": scored.get("tomorrow", {}).get("live_count"),
|
| 2045 |
+
}
|
| 2046 |
+
)
|
| 2047 |
+
except Exception as exc:
|
| 2048 |
+
actions.append({"name": "tomorrow_live_accuracy", "error": str(exc)})
|
| 2049 |
+
|
| 2050 |
+
if status["daily_stale"] or status["tomorrow_stale"]:
|
| 2051 |
+
try:
|
| 2052 |
+
tomorrow = refresh_tomorrow_prediction(session_date=date.fromisoformat(status["expected_daily_date"]))
|
| 2053 |
+
actions.append({"name": "tomorrow_prediction", "input_date": tomorrow.get("input_date")})
|
| 2054 |
+
except Exception as exc:
|
| 2055 |
+
actions.append({"name": "tomorrow_prediction", "error": str(exc)})
|
| 2056 |
+
|
| 2057 |
+
if status["t5_stale"] and is_trading_day(now.date()) and now.time() >= FIRST5_READY:
|
| 2058 |
+
prediction = refresh_first5_prediction(session_date=now.date())
|
| 2059 |
+
actions.append({"name": "t5_prediction", "input_date": prediction.input_date})
|
| 2060 |
+
|
| 2061 |
+
if status["tplus1_stale"] and is_trading_day(now.date()) and now.time() >= TPLUS1_READY:
|
| 2062 |
+
prediction = refresh_tplus1_prediction(session_date=now.date())
|
| 2063 |
+
actions.append({"name": "tplus1_prediction", "input_date": prediction.get("input_date")})
|
| 2064 |
+
|
| 2065 |
+
clear_dashboard_payload_cache()
|
| 2066 |
+
refreshed_status = stale_data_status(datetime.now(IST))
|
| 2067 |
+
return {"status": "refreshed", **refreshed_status, "actions": actions}
|
| 2068 |
+
finally:
|
| 2069 |
+
_stale_refresh_lock.release()
|
| 2070 |
+
|
| 2071 |
+
|
| 2072 |
+
def next_ist_run_at(run_time: time = time(9, 20), now: datetime | None = None) -> datetime:
|
| 2073 |
now = now or datetime.now(IST)
|
| 2074 |
target_day = now.date()
|
| 2075 |
if now >= datetime.combine(target_day, run_time, tzinfo=IST):
|