jerry-thomas 0.3.0__py3-none-any.whl → 1.0.0__py3-none-any.whl

jerry_thomas-1.0.0.dist-info/RECORD

@@ -0,0 +1,199 @@
+datapipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+datapipeline/plugins.py,sha256=Y0QfI313t5_w_m1ayQVEuac3lJ4YR_OSIYZol35ZOTk,838
+datapipeline/runtime.py,sha256=yfSlQaq9OdjVVuqRtWzxLdw1ku4boZoONfCYQIMfe3A,2622
+datapipeline/analysis/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+datapipeline/analysis/vector_analyzer.py,sha256=D6eDW0H55QGnWiULXJEirMjw6MeBcwjJ4zfS7M6tx98,175
+datapipeline/analysis/vector/collector.py,sha256=J-a42GiTqjGlhXFfz3LCa2QzeWqRTOoaGE4E_HGKhOs,14762
+datapipeline/analysis/vector/matrix.py,sha256=pzaMmEMD09cOlRbBzuD0Lgc91dtKnCdCkJAXtkcCOPc,18469
+datapipeline/analysis/vector/report.py,sha256=OsSarYX4-CWwdKI3b35qBqrhHxShavFS9CeYKZ7WTRs,16709
+datapipeline/build/__init__.py,sha256=XbuHhJzIRTNnOOJMYa_BHiA0P8yPrEk4tuVXnD2NQbI,109
+datapipeline/build/state.py,sha256=XsL2CtQl7x80OpE1SJE42D-ig3lBMPr7_HSlpq5xwU4,1826
+datapipeline/build/tasks/__init__.py,sha256=-HRDBwLY9eLsKxjDzsC-E10y_ytfhOs9yXVA_Nyt4_o,319
+datapipeline/build/tasks/config.py,sha256=8cuX5nEWFesWoZHWfeTNMlXqsE_dsPgYf6x2eyz1l0c,2312
+datapipeline/build/tasks/metadata.py,sha256=3eHI1vBRwm-fT342gu1wgj7oXNXKZ94D30wkdAVA7kM,5783
+datapipeline/build/tasks/scaler.py,sha256=knJbdeGdDvYZ4O15ra4mnVkmLZbRZbCdJdjfELe_LnU,2554
+datapipeline/build/tasks/schema.py,sha256=kJnAlD_Z8Pd_c9kJH5bDVixB_Vi_mBkKWpjW7eZru1s,2163
+datapipeline/build/tasks/utils.py,sha256=iFMJ8hWk1iRnQ1bUz0huiKlWyevt3x0g8Vh6PNzlMU8,6335
+datapipeline/cli/app.py,sha256=yjaKjEbQbDUAvigU5D8Q2UPbKFRs9l8bHVIG-56Nrsc,24056
+datapipeline/cli/commands/build.py,sha256=OPJ-r3WWAzWwa1wHK0zxnQhuM_1h1mSfNpPRl_Bqrf8,8979
+datapipeline/cli/commands/contract.py,sha256=bPWhWZgdnkk_Ajlm9zUJrvZ3SlyXVqBxx-IJV1zZ5kM,14953
+datapipeline/cli/commands/domain.py,sha256=JdOMlfpZP996kuNGePdjCGMKrqezo-cX8lhlOfd9F44,479
+datapipeline/cli/commands/filter.py,sha256=vhoCIETJNUJmiI37ZdBNaeJAm6O4AU_tveJxVj47S8A,307
+datapipeline/cli/commands/inspect.py,sha256=aatn_olRcFaLyya6r2QMlzzAzlbguEtQ7mKRxoEOFAA,16066
+datapipeline/cli/commands/list_.py,sha256=m9o_exiiC_aiQXsR4lZv_QmN1hfpSNq4ICvYLgiS2e8,1605
+datapipeline/cli/commands/plugin.py,sha256=RER1aBiiITYyvCtWxaqAiEqUGJGzKhw6oWSeajtd5ns,374
+datapipeline/cli/commands/run.py,sha256=TmbyggYOlF972oxwLhh-r27ggeWARg0_WfCMQJAudS8,8348
+datapipeline/cli/commands/run_config.py,sha256=zeXCuDz1ez6Zd6Tq2N0S-YIPs1ZQ8U3fN3lvvd56108,3194
+datapipeline/cli/commands/serve_pipeline.py,sha256=7i1HbuFIbYKkM-aQ2BrDN57K1kFv6NJ4EAN6NOz4aFE,5036
+datapipeline/cli/commands/source.py,sha256=OyDOZm93Lbj6avbAefQPWX87WfRWE1phCPVPB-dNVc4,2073
+datapipeline/cli/visuals/__init__.py,sha256=CUxCoMoU96FQonq6V_i_HBUwuwoWjML5X-_MZDF_i8M,371
+datapipeline/cli/visuals/common.py,sha256=p66-3WBMfl7_3UVIfsrkXnzpE9BsHinpmkHWOZaK00c,8173
+datapipeline/cli/visuals/labels.py,sha256=oK1PpgMoGhlwfyTqiXuaaDm65gDYqv9R-Ac8NqYPhHE,2680
+datapipeline/cli/visuals/runner.py,sha256=GtQcFjmYfVuNMmmp3uoJo0sXJOGeCoN6EOUUB6kzWSU,2085
+datapipeline/cli/visuals/sections.py,sha256=ZK02cjxd5FJAF-IJXqj9loWSrlWwMfYJlbsCfmLBJ5A,614
+datapipeline/cli/visuals/sources.py,sha256=m0nNmRSlSNWTyGj_MF3PS_m9hXKtJv63bP_9-SKn0Xc,5144
+datapipeline/cli/visuals/sources_basic.py,sha256=1-1JJ77AdiQv0iC4qpvb71cICmheInusIJFCc3csWLs,9086
+datapipeline/cli/visuals/sources_off.py,sha256=8nWuwsj-XBsjcfZ9FBpuxC3vhC6mPPObjVsh1EUparM,2651
+datapipeline/cli/visuals/sources_rich.py,sha256=W2ziT0Sb0QKhEbEjPYVUMY0TOrOhey0X3LXjNSwQHLg,16577
+datapipeline/config/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+datapipeline/config/catalog.py,sha256=2eMwiCEof3WWKASfhxLNaZHLHCqXBoUtdJ1LvHUT74Y,2552
+datapipeline/config/context.py,sha256=JzkhFHeSYuyID5L2FPSinA3S0Gx7BNsXXfy_adAjNHI,6857
+datapipeline/config/metadata.py,sha256=Vckaz6P7_MparAR3IOWR5K5S5mqqul2F6wEg3DWMyzw,1309
+datapipeline/config/postprocess.py,sha256=67ukmtGNHFmZd8bv-POWOE_HjE5T5AXQaOypCZG1d-o,361
+datapipeline/config/project.py,sha256=nc2n9g-02pOmuErzHHxJasP4wn04rB7rXqIUieYg_vQ,997
+datapipeline/config/resolution.py,sha256=syS9fLWNl17NrA-GPpAk3pbFtL4I7hQDJdfWaeldqXs,3477
+datapipeline/config/split.py,sha256=VFYRF6Fz5xLTqqxIt3RVGB4kwlnHH8CxjOddEAJYG5Q,1048
+datapipeline/config/tasks.py,sha256=qRHV6vEOWgpfknSplfV7RbCAdcIsAVcfk2NZU92zRsE,9777
+datapipeline/config/workspace.py,sha256=mcZxnEtV2rNkb7TeeE7P_C-LIgQ27e10CawW1w4H7w0,5131
+datapipeline/config/dataset/dataset.py,sha256=Q9cb5QoDtyPb4pbD9mSTZcJmXQhdEWwDLS52xKAcqXg,562
+datapipeline/config/dataset/feature.py,sha256=2Hxz0FXZskLI4ICXhmlG6b1Vvxzh0Ql9e6BwjMRtzSs,346
+datapipeline/config/dataset/loader.py,sha256=Eh_F56o242ptEIsR22kC7HkNi6SggpRf10Gpfc3ipTo,1063
+datapipeline/config/dataset/normalize.py,sha256=5IFGYhRrJ4JMWLLy-qRc6W8p6FZr8T-Fz2FCxp6MHCA,803
+datapipeline/domain/__init__.py,sha256=rfZZpfvozmQNKhBabzgC9g4urMbchjDXbbl54sNtxZQ,262
+datapipeline/domain/feature.py,sha256=7BOI4H458BKU8B9vqdfez7WOO1YKiF6lt0oy7PMbqrQ,295
+datapipeline/domain/record.py,sha256=VY2vxpVJGpn0sztI5mvD0oPdxy5auLJ8huKUR1VCgZA,1062
+datapipeline/domain/sample.py,sha256=yjmxPJmjHwrw9xJR5hxFr1XKelpJEOZI7XrLlqsrzy4,1558
+datapipeline/domain/vector.py,sha256=apK1iu7tca2k2xgNGJAAQfKhirno7ZKZ3pDheKf9euM,1041
+datapipeline/filters/filters.py,sha256=dM6U-QpGCQQ4-CMBTJgWZp2zH2TVTk6uYOqGPC5NBCY,2649
+datapipeline/integrations/__init__.py,sha256=tjTLsIa6NRWKI05wjwPAUuXozDA-gP98SccFJ9lYHs8,410
+datapipeline/integrations/ml/__init__.py,sha256=oflJXnjQEn1Zv0Vho10mc2y3D6UkKusNZwE5yUtatb8,463
+datapipeline/integrations/ml/adapter.py,sha256=X9UGbNev4eN-KhL8KAaSPKLrpkrgJA3c0sTgFRDAMv0,4591
+datapipeline/integrations/ml/pandas_support.py,sha256=HEX-Dx9RG17uCKSiZ7M4gMCoZbMQTa_3xhlC0s6bIYM,1229
+datapipeline/integrations/ml/rows.py,sha256=OhziMyP6uvFFErYYJkaQkaXQ4oX-jAXnIDazLUfhP5A,1995
+datapipeline/integrations/ml/torch_support.py,sha256=RCQaOCaggddtAo67-ThkdX_GgVJyLCHGZs3YyOszF04,2703
+datapipeline/io/factory.py,sha256=xChYRxe1SRxHj8SXNirPEi2J20AOH3968yN92BRykr8,3903
+datapipeline/io/output.py,sha256=tbtE4iJTDNtQcburA6W25eGH0gX-hAoVMLas5slkVAA,4003
+datapipeline/io/protocols.py,sha256=vHjXhuV2r1Lo7k8SJuPH0WL2EXG_nm3DBpSowobUZ2U,512
+datapipeline/io/serializers.py,sha256=5g59YwEL4-FT2r5kSj3UoQCKFkn-va2EMA8z79YzA18,6380
+datapipeline/io/sinks/__init__.py,sha256=7l-LmJAjuNrQZWMDFMXdjbZQ4Pq-iWMaN_3GcUvWntw,517
+datapipeline/io/sinks/base.py,sha256=cXG6VXop0RVL1K4xpSaFq1scylhb6N6dsg6UMrQGw54,49
+datapipeline/io/sinks/files.py,sha256=UgXXj8NxjvdOrwpJt5YNTgG1gW89YYCVpVkSg1eGgKI,1975
+datapipeline/io/sinks/rich.py,sha256=hZNMttsqaMSUsQmCu6kubzkYbUGDTbTYBYnDwcFsEp0,1486
+datapipeline/io/sinks/stdout.py,sha256=64VUdf_YghxTCjVyYcpBQpC_Pt5rPQrYejRg_0_cF7A,382
+datapipeline/io/writers/__init__.py,sha256=V8228IYVxP4ay6yG8HF_ukBDseAERrqlWC4gbGDBmoc,397
+datapipeline/io/writers/base.py,sha256=kUaFv6XOoUjYw5pE7XFUel5ptdEhuY03VTqajortUZY,814
+datapipeline/io/writers/csv_writer.py,sha256=FL2qiS8Hr273lGcN6pQXGOSufcM06ApVZnPmNhuAwjQ,833
+datapipeline/io/writers/jsonl.py,sha256=SP2yPgH4B_Xrr7GJFVVIsTxarNKAFbEB-0RS1F0fD-g,1736
+datapipeline/io/writers/pickle_writer.py,sha256=omXSeGbrcSWwNBodwJNCBok0mW167xciT5S8w_w5xCo,928
+datapipeline/mappers/noop.py,sha256=L8bH1QVbLH-ogIam0ppYdx7KuWQ7Dj44lvD8tvNlY0Q,111
+datapipeline/mappers/synthetic/time.py,sha256=lt1pC0May6Y4E8bZO4sERm3D04_r-qv63Y5fwrtCaBQ,639
+datapipeline/parsers/identity.py,sha256=pdGuz0SSQGfySPpvZSnLgfTXTkC36x-7dQMMei3XhsU,321
+datapipeline/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+datapipeline/pipeline/artifacts.py,sha256=mD31N-tlFR3EePVHNaxyA3Diiqab9Kyc0Gh6jCX_z-g,1492
+datapipeline/pipeline/context.py,sha256=-W8QvGm32QGmBziEuzl-BitscuxGPb9bgQYDhRC1tkc,4377
+datapipeline/pipeline/observability.py,sha256=y5LWgY3vjlhA5paslWVkjtMjur8yAGXjFhYNrfuJUNg,2043
+datapipeline/pipeline/pipelines.py,sha256=Ilys2Cyqee5kHQ_gTIwWr4UZNDvyhU_xxUhBj42b5yI,4274
+datapipeline/pipeline/split.py,sha256=TCzOhd8PF81IcUzUdPSz0hs3pIHi9V4IhXbSY2ZHK3Q,6090
+datapipeline/pipeline/stages.py,sha256=yWl7nCJt_kOh9VVLgM6fDFM0Ajgh0GCwtvA-gSDRHTs,9493
+datapipeline/pipeline/utils/keygen.py,sha256=v2JJagJAE9iYfLtbl4uxoAEXZN_ALH0xdHhPDhNfKwU,1909
+datapipeline/pipeline/utils/memory_sort.py,sha256=hS61n2CeIITRqffE1ftvn2IdqQp1IXYhuN4MJqncKvk,1155
+datapipeline/pipeline/utils/ordering.py,sha256=ZX18I7GFtvyMFJB96vWQpTOGwljjeJ6ppCg5a3Av3es,1450
+datapipeline/pipeline/utils/transform_utils.py,sha256=q4bxQ0NFC4G7IeRSSL4ZzQ7vvVkxAnovflhEtfVUXyU,4221
+datapipeline/registries/registry.py,sha256=MWWOHz2wT1oHQmovodtEreEuQhvH-i11Y2yXUUgZJhQ,641
+datapipeline/services/artifacts.py,sha256=5mqNs5G53RqOYlMGvF0-_ZZA1M8mMMUXip1HuFhckjI,2930
+datapipeline/services/constants.py,sha256=OVUqBBDkpl-A_f71uT8QUwd_50fgN1pA6uL4Yv8ZpUE,517
+datapipeline/services/entrypoints.py,sha256=NKcSbhGRtBLQXGf-TdujwbVSRH1zb5J-S2jxFPnk6HQ,2504
+datapipeline/services/factories.py,sha256=4Udq2LBRHNJmBTZiXrbqmV6PVbesg2c5Nndh6CpYDnE,6011
+datapipeline/services/paths.py,sha256=xHxos62Y2gjhLggrnrmRqPiLMseK10OX17NJjnVk8wE,966
+datapipeline/services/project_paths.py,sha256=qWM5WN0aKB4KwkwXgZQywBFPu1Cfh9mUiAQZghRwNOs,4264
+datapipeline/services/runs.py,sha256=_xcrgZXb3sFfRN1ohvTLicQHq7_33g62SCt_JXCOzqE,6185
+datapipeline/services/bootstrap/__init__.py,sha256=Mc2w2S69kU1hnzCvsGMhFqyNoNMXPwQtxprAkGN-sYE,245
+datapipeline/services/bootstrap/config.py,sha256=122JNE7gZF1mohAI1gvX8H6i0JTql_Mm9bWcTpoD77c,4936
+datapipeline/services/bootstrap/core.py,sha256=7iWf05GRdIOvgEHKOoq5NUFAMNhkd_kTe3zunkJqOHw,7394
+datapipeline/services/scaffold/__init__.py,sha256=PaQNtYki9Kc7mQPnUtKDPU-rKohLHoXLvFVwdHdbXNM,68
+datapipeline/services/scaffold/domain.py,sha256=mww7HhZ1ZepNvn2tHczpLZH0y3Ej7vgDGVLepFkTgIY,946
+datapipeline/services/scaffold/filter.py,sha256=EwLFeI3cRoHw-hYE3jlLfqV0DKk9Z8EnWyVymJmOppA,1084
+datapipeline/services/scaffold/mappers.py,sha256=kkkJ-UB51B2yawRoUst3CGExn3gRYPm5d_3kbujPVMQ,1960
+datapipeline/services/scaffold/plugin.py,sha256=bocH4Z1k3ReqnfLSzdXLiQP4SG9R97kZ5hj14_7GYFM,1699
+datapipeline/services/scaffold/source.py,sha256=w0w-oID9x48eMV6c0FhqW1myAWh_ELYmFojsdfVlaTk,6649
+datapipeline/services/scaffold/templates.py,sha256=B3YnZpFUZLynijJosTNxZQLXnPP_Y_t1RHqfI1lGOxU,634
+datapipeline/sources/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+datapipeline/sources/data_loader.py,sha256=q-gAQDOkMwIvY5b-T0j6P_Bj716R5I7jIoyHOleTB2s,1358
+datapipeline/sources/decoders.py,sha256=yH4uVDg0Hh6sUpk04W3u1dtJi_Xv-vPhvlMEIGs7-zs,3984
+datapipeline/sources/factory.py,sha256=UkcrycyodBBGt7Q5EO8EirH4obnOQH8SqrFedjMEIR0,2410
+datapipeline/sources/transports.py,sha256=o32uvCRWps-voresZ2gGwhXTiRpmDIWdyM_IE2zY0H8,3308
+datapipeline/sources/models/__init__.py,sha256=_DVhnet2HMvw-H-UEFQeEXCwro6Qg1ws0iBgMSKbBbM,399
+datapipeline/sources/models/base.py,sha256=MAUawd11fII-mxxuSPM4f6H1t1tbyZX_QWhoAgeYUcU,238
+datapipeline/sources/models/generator.py,sha256=OTJEcbpRp6pPZyG_8sds2x-15LF-SvAR5yblivG1E2g,508
+datapipeline/sources/models/loader.py,sha256=VMWfEzrBvKdtRPjixPbttTochO3IULdglJ01769310E,1028
+datapipeline/sources/models/parser.py,sha256=Ts31aksHLDCw5ovF2D99w9g_j-NnEiZ8x0JHtUxmmXs,226
+datapipeline/sources/models/parsing_error.py,sha256=41pmauyqNK75Hke-rauRRNc-UveNXt8czxCViyZidvs,734
+datapipeline/sources/models/source.py,sha256=lcAcbwM-HrMVO3uEWTpbvqY42g74JZWKD-KJ89Lsjys,913
+datapipeline/sources/models/synthetic.py,sha256=FLF2Jvdc06VCriTCliThuQTUXd6NrXIQpksIL8gBIH8,288
+datapipeline/sources/synthetic/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+datapipeline/sources/synthetic/time/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+datapipeline/sources/synthetic/time/loader.py,sha256=X_NQJFAHL8wHV5TxbLhRwqGfFJPOw6qVToBkKFD3r_k,2003
+datapipeline/sources/synthetic/time/parser.py,sha256=d3GZMQ7L1Qi4LeEm7U3y0_pk0RdhskioQukYyqyoqic,343
+datapipeline/templates/plugin_skeleton/README.md,sha256=lRaDeFPK-r1qPUYmPkTztfHptVfbxlKmCOgKaAJJaHc,7490
+datapipeline/templates/plugin_skeleton/jerry.yaml,sha256=ubM5REHH5gEqbCBuUIBXRsSx6iuJjQ96yzn7RQBDMpk,705
+datapipeline/templates/plugin_skeleton/pyproject.toml,sha256=0lmO5Aia9tB81Ez4SxP56DGisekx-palMmGCUzmAl4E,259
+datapipeline/templates/plugin_skeleton/example/dataset.yaml,sha256=cSKk8IyoJebdc9b959Sw7gDfBXl2BT8hktyZ4Z43Nog,471
+datapipeline/templates/plugin_skeleton/example/postprocess.yaml,sha256=yUYr5c6YtBeF_rm_ENsOMkn_sOAChzbqhL98WKr0CRw,710
+datapipeline/templates/plugin_skeleton/example/project.yaml,sha256=4WyrlBCZZ47ceOw9nV8QgqU7_jH5Fu8-z4SJGKbPYK8,845
+datapipeline/templates/plugin_skeleton/example/contracts/time.ticks.hour_sin.yaml,sha256=oHesyqPHQ6KYJeVNxZlB75Pw0BTezr2U9IhsdM6YQ7E,842
+datapipeline/templates/plugin_skeleton/example/contracts/time.ticks.linear.yaml,sha256=jtxL89bgdi84iUp4lcMUCZZGcxXsSmTaFOyfe5rxX-M,1579
+datapipeline/templates/plugin_skeleton/example/sources/synthetic.ticks.yaml,sha256=bouMA0PdRETU67wkh8HTs7vzr0UkKcVXDjAoVChdHAc,210
+datapipeline/templates/plugin_skeleton/example/tasks/metadata.yaml,sha256=IMeokmMOFwY1jrXauoFtTFV6gtdos9xFob7nCrqfkPA,104
+datapipeline/templates/plugin_skeleton/example/tasks/scaler.yaml,sha256=xNl8JmJ4ogHtfq1jpNqMvH4GYWgxFJ0vMqB6XI3aM-g,237
+datapipeline/templates/plugin_skeleton/example/tasks/schema.yaml,sha256=Y5X3lOM-0FwKNjFLTeRtts6FZjSj2mLpsO4CS2GBafs,14
+datapipeline/templates/plugin_skeleton/example/tasks/serve.test.yaml,sha256=YXGYz3szsA92Qejdm3KdKYac3aFPPlnfnhipufGYzsA,35
+datapipeline/templates/plugin_skeleton/example/tasks/serve.train.yaml,sha256=9LFcjdkGYtz2WifCB-6avrvB-5TZUGBCJFQQbuFoQPk,910
+datapipeline/templates/plugin_skeleton/example/tasks/serve.val.yaml,sha256=ecV69-l6qQS2jIagh1SuehxfLdIBeR49uekhC6DB6EM,33
+datapipeline/templates/plugin_skeleton/src/{{PACKAGE_NAME}}/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+datapipeline/templates/plugin_skeleton/your-dataset/dataset.yaml,sha256=cSKk8IyoJebdc9b959Sw7gDfBXl2BT8hktyZ4Z43Nog,471
+datapipeline/templates/plugin_skeleton/your-dataset/postprocess.yaml,sha256=yUYr5c6YtBeF_rm_ENsOMkn_sOAChzbqhL98WKr0CRw,710
+datapipeline/templates/plugin_skeleton/your-dataset/project.yaml,sha256=u9LtgLt6OdLsPd7r4bmrujg87WX8NzQBNIvI3gs3QgQ,827
+datapipeline/templates/plugin_skeleton/your-dataset/contracts/time.ticks.hour_sin.yaml,sha256=oHesyqPHQ6KYJeVNxZlB75Pw0BTezr2U9IhsdM6YQ7E,842
+datapipeline/templates/plugin_skeleton/your-dataset/contracts/time.ticks.linear.yaml,sha256=jtxL89bgdi84iUp4lcMUCZZGcxXsSmTaFOyfe5rxX-M,1579
+datapipeline/templates/plugin_skeleton/your-dataset/sources/synthetic.ticks.yaml,sha256=bouMA0PdRETU67wkh8HTs7vzr0UkKcVXDjAoVChdHAc,210
+datapipeline/templates/plugin_skeleton/your-dataset/tasks/metadata.yaml,sha256=IMeokmMOFwY1jrXauoFtTFV6gtdos9xFob7nCrqfkPA,104
+datapipeline/templates/plugin_skeleton/your-dataset/tasks/scaler.yaml,sha256=xNl8JmJ4ogHtfq1jpNqMvH4GYWgxFJ0vMqB6XI3aM-g,237
+datapipeline/templates/plugin_skeleton/your-dataset/tasks/schema.yaml,sha256=Y5X3lOM-0FwKNjFLTeRtts6FZjSj2mLpsO4CS2GBafs,14
+datapipeline/templates/plugin_skeleton/your-dataset/tasks/serve.test.yaml,sha256=YXGYz3szsA92Qejdm3KdKYac3aFPPlnfnhipufGYzsA,35
+datapipeline/templates/plugin_skeleton/your-dataset/tasks/serve.train.yaml,sha256=9LFcjdkGYtz2WifCB-6avrvB-5TZUGBCJFQQbuFoQPk,910
+datapipeline/templates/plugin_skeleton/your-dataset/tasks/serve.val.yaml,sha256=ecV69-l6qQS2jIagh1SuehxfLdIBeR49uekhC6DB6EM,33
+datapipeline/templates/stubs/dto.py.j2,sha256=MizqUzY4eGXiIHzGBovXoPHqhVno791Bi6PCGigVqww,908
+datapipeline/templates/stubs/filter.py.j2,sha256=3LgRgAL_HRaENOOqQx8NdeM1AUy-T0rtHVTA7N2oWOs,466
+datapipeline/templates/stubs/loader_synthetic.py.j2,sha256=9SQBeTBGlZmKs6nSYBKd8nbOPcFHgDx17Mh8xOEQnvs,1285
+datapipeline/templates/stubs/mapper.py.j2,sha256=eonMmBgql-XFnxcQ5mRONyPCJShhQAp1jqYSF_1Pcvo,783
+datapipeline/templates/stubs/parser.py.j2,sha256=Ie6ykkT4YTNlRTlbagleHnFukwewHRTq7C7Tbg_P_9Y,674
+datapipeline/templates/stubs/parser_custom.py.j2,sha256=0Nytq43JdTZoyRj-4Mz6HWdMTmOP3VlFuYOB_A_13Vg,580
+datapipeline/templates/stubs/record.py.j2,sha256=xiDMMbYmoReBy0KXRoFcd9FuUoLi9kYzlMFmFjdE4WE,662
+datapipeline/templates/stubs/source.yaml.j2,sha256=pKxqYuJsD5TkVHjT4UrwWQ2RFc0JoL0w3YnZqZgf5J0,410
+datapipeline/transforms/filter.py,sha256=Jt8wTEIqWqe34s7GVVekcR8OdRozs317sj7Uw08GNOA,1433
+datapipeline/transforms/sequence.py,sha256=tZiqFB_aZdVji2uEaFkUyah8k4AYX9IxPMoLBbOCfYg,1579
+datapipeline/transforms/utils.py,sha256=ts6dULY2Pc5fFs7AMd3goN4hDzQkv-6CDLdRH41lG9I,721
+datapipeline/transforms/vector_utils.py,sha256=PcStTwRaaunONKZJuwv79bjdfaDcamLcwNLRHjZ5yXw,927
+datapipeline/transforms/debug/identity.py,sha256=6bwnEYhMBYw0YPrMccrZPXDOQM4r_-odsKo8Hhpbz10,2515
+datapipeline/transforms/debug/lint.py,sha256=v7aLig0y7K_Wqc4W37ZVfUmyLXOV8gcgDMBHm-QzUo0,3124
+datapipeline/transforms/feature/model.py,sha256=gB-GP80_P7bzEKJFSM4leRke75yiD4-S5eJ1p8g3JU8,382
+datapipeline/transforms/feature/scaler.py,sha256=-NRQCz_BUG5X7sg4adMXxZ-1AOAhdmdHET1uIkBPWR0,8305
+datapipeline/transforms/record/floor_time.py,sha256=Nk_srdwNMuxqRCguxjvFKB7rfzMu1SB1pDYVh4cdV4Q,617
+datapipeline/transforms/record/lag.py,sha256=5wrPyVNFvidvdQddnK6ZeUOI5I8rfXEbzIg6tzKiJu4,536
+datapipeline/transforms/stream/dedupe.py,sha256=VyKI8hMcekBntjD3WjIBykMiPs8RNkxQSpd9SCwxihA,787
+datapipeline/transforms/stream/ensure_ticks.py,sha256=hxnG3yHabt4HeOYjWyhMrIBxG1ZbG1uj8vEM4WtGEfA,1185
+datapipeline/transforms/stream/fill.py,sha256=N_ybLUCvaMVvKsFP8-HcGuKqV9hXAnYmV7zyUB-Ugys,3500
+datapipeline/transforms/stream/granularity.py,sha256=PzHDGDwyn8P07BCbcFZaorS_7lbAbEdMLqD9Wy61y0M,3376
+datapipeline/transforms/vector/__init__.py,sha256=nKBaksXv_rBF2BUT-IFJTbbRBiwkpq6k39cLFS8CfXw,245
+datapipeline/transforms/vector/common.py,sha256=24iX5EviN9BKi9-GJIty57LGOvEVD9PueZflyoGS5Nc,3616
+datapipeline/transforms/vector/ensure_schema.py,sha256=AByCuHhnC7T4CWgk5oUC59-oom_LzC0aER1WBASEkDs,7240
+datapipeline/transforms/vector/fill.py,sha256=1bWXbVABnyndv4O01cZN0oVS2-X_HVAEGUmwywazs_w,3065
+datapipeline/transforms/vector/replace.py,sha256=gYTZx0CTkdSsuXUiAvP7dtcyEHEQv2UJeIEiowGDzhw,2019
+datapipeline/transforms/vector/drop/__init__.py,sha256=NsGv9v7n13uPsRWGTSLKWPVaXocQ-zx9WE3Ez5hQt3U,151
+datapipeline/transforms/vector/drop/horizontal.py,sha256=c6bsOaKrppEfBQoNGOaWLbKUHWPlLCo9jscBDYMvEp8,2567
+datapipeline/transforms/vector/drop/orchestrator.py,sha256=smd3z9Oz5iEzkahButE5UsK1nPrSUw6B5CPxtfj2K8g,1986
+datapipeline/transforms/vector/drop/vertical.py,sha256=5VBtilX48Pw6Fc1e0UGk6IwIUoPbkm98t2N7EPql1gA,6858
+datapipeline/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+datapipeline/utils/load.py,sha256=FfW_UOD5NhxDg4DarRSzVbjGbv7An_bKK-IdUUOrFhs,1970
+datapipeline/utils/paths.py,sha256=5Y5rhNbjTiybUHfq9VfRMJ4gUfN9UltonM-4MABEG8w,798
+datapipeline/utils/pickle_model.py,sha256=Uyd4AajInyTUpWfSJDDEGLinXeQkHjQUNnyla0owtA4,854
+datapipeline/utils/placeholders.py,sha256=epZQ7NifUWI7_7hZKGEkCBDOaMnN9LiqJdI2gvBAEgE,890
+datapipeline/utils/rich_compat.py,sha256=4ZfR82gG1vAVUiILVINqcRReqoUiRPmQOlLLBXz-pC0,1166
+datapipeline/utils/time.py,sha256=vOqa2arqwEqbDo-JWEhOFPMnI1E4Ib3i1L-Rt-cGH8c,1072
+datapipeline/utils/window.py,sha256=J5CkEIdY5iZd1QY9wawmHpBXpCp2FzHOHXhjYTCZWl8,2576
+jerry_thomas-1.0.0.dist-info/licenses/LICENSE,sha256=pkBMylAJF5yChHAkdxwFhEptLGx13i-XFEKh-Sh6DkM,1073
+jerry_thomas-1.0.0.dist-info/METADATA,sha256=lcnvJMQUbZ_cECGZhmkZz0zOvGZlVOtym3A1X_SaVNw,33507
+jerry_thomas-1.0.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+jerry_thomas-1.0.0.dist-info/entry_points.txt,sha256=jsJFp_2aEEhKkL2I3Yc4yPSODy9ggDZmLeV75KPjb9A,1672
+jerry_thomas-1.0.0.dist-info/top_level.txt,sha256=N8aoNPdPyHefODO4YAm7tqTaUcw0e8LDcqycFTf8TbM,13
+jerry_thomas-1.0.0.dist-info/RECORD,,

{jerry_thomas-0.3.0.dist-info → jerry_thomas-1.0.0.dist-info}/entry_points.txt

@@ -2,16 +2,17 @@
 jerry = datapipeline.cli.app:main
 
 [datapipeline.loaders]
-composed.loader = datapipeline.sources.factory:build_loader
-synthetic.time = datapipeline.sources.synthetic.time.loader:make_time_loader
+core.io = datapipeline.sources.factory:build_loader
+core.synthetic.ticks = datapipeline.sources.synthetic.time.loader:make_time_loader
 
 [datapipeline.mappers]
 encode_time = datapipeline.mappers.synthetic.time:encode
+identity = datapipeline.mappers.noop:identity
 time.synthetic = datapipeline.mappers.noop:identity
 
 [datapipeline.parsers]
+core.synthetic.ticks = datapipeline.sources.synthetic.time.parser:TimeRowParser
 identity = datapipeline.parsers.identity:IdentityParser
-synthetic.time = datapipeline.sources.synthetic.time.parser:TimeRowParser
 
 [datapipeline.transforms.debug]
 identity = datapipeline.transforms.debug.identity:IdentityGuardTransform
@@ -27,13 +28,13 @@ floor_time = datapipeline.transforms.record.floor_time:floor_time
 lag = datapipeline.transforms.record.lag:apply_lag
 
 [datapipeline.transforms.stream]
-ensure_ticks = datapipeline.transforms.stream.ensure_ticks:ensure_ticks
+dedupe = datapipeline.transforms.stream.dedupe:FeatureDeduplicateTransform
+ensure_cadence = datapipeline.transforms.stream.ensure_ticks:ensure_cadence
 fill = datapipeline.transforms.stream.fill:FillTransformer
 granularity = datapipeline.transforms.stream.granularity:FeatureGranularityTransform
 lint = datapipeline.transforms.stream.lint:StreamLint
 
 [datapipeline.transforms.vector]
-drop_missing = datapipeline.transforms.vector:VectorDropMissingTransform
-fill_constant = datapipeline.transforms.vector:VectorFillConstantTransform
-fill_history = datapipeline.transforms.vector:VectorFillHistoryTransform
-fill_horizontal = datapipeline.transforms.vector:VectorFillAcrossPartitionsTransform
+drop = datapipeline.transforms.vector:VectorDropTransform
+fill = datapipeline.transforms.vector:VectorFillTransform
+replace = datapipeline.transforms.vector:VectorReplaceTransform

datapipeline/build/tasks.py

@@ -1,186 +0,0 @@
-from __future__ import annotations
-
-import hashlib
-from pathlib import Path
-from typing import Dict, Iterable, Iterator, Sequence, Tuple
-
-from datapipeline.config.build import BuildConfig
-from datapipeline.config.dataset.loader import load_dataset
-from datapipeline.pipeline.context import PipelineContext
-from datapipeline.pipeline.pipelines import build_vector_pipeline
-from datapipeline.pipeline.split import build_labeler
-from datapipeline.runtime import Runtime
-from datapipeline.services.constants import PARTIONED_IDS, SCALER_STATISTICS
-from datapipeline.services.project_paths import read_project
-from datapipeline.utils.paths import ensure_parent
-from datapipeline.transforms.feature.scaler import StandardScaler
-
-
-def _resolve_relative(project_yaml: Path, value: str) -> Path:
-    path = Path(value)
-    return path if path.is_absolute() else (project_yaml.parent / path)
-
-
-def _normalized_label(path: Path, base_dir: Path) -> str:
-    try:
-        return str(path.resolve().relative_to(base_dir))
-    except ValueError:
-        return str(path.resolve())
-
-
-def _hash_file(hasher, path: Path, base_dir: Path) -> None:
-    hasher.update(_normalized_label(path, base_dir).encode("utf-8"))
-    hasher.update(b"\0")
-    hasher.update(path.read_bytes())
-    hasher.update(b"\0")
-
-
-def _yaml_files(directory: Path) -> Iterable[Path]:
-    if not directory.exists():
-        return []
-    return sorted(p for p in directory.rglob("*.y*ml") if p.is_file())
-
-
-def compute_config_hash(project_yaml: Path, build_config_path: Path) -> str:
-    """Compute a deterministic hash across relevant config inputs."""
-
-    hasher = hashlib.sha256()
-    base_dir = project_yaml.parent.resolve()
-    cfg = read_project(project_yaml)
-
-    required: Sequence[Path] = [
-        project_yaml.resolve(),
-        build_config_path.resolve(),
-        _resolve_relative(project_yaml, cfg.paths.dataset).resolve(),
-        _resolve_relative(project_yaml, cfg.paths.postprocess).resolve(),
-    ]
-
-    for path in required:
-        if not path.exists():
-            raise FileNotFoundError(f"Expected config file missing: {path}")
-        _hash_file(hasher, path, base_dir)
-
-    for dir_value in (cfg.paths.sources, cfg.paths.streams):
-        directory = _resolve_relative(project_yaml, dir_value)
-        hasher.update(
-            f"[dir]{_normalized_label(directory, base_dir)}".encode("utf-8"))
-        if not directory.exists():
-            hasher.update(b"[missing]")
-            continue
-        for path in _yaml_files(directory):
-            _hash_file(hasher, path, base_dir)
-
-    return hasher.hexdigest()
-
-
-def _collect_partitioned_ids(runtime: Runtime, include_targets: bool) -> Sequence[str]:
-    dataset = load_dataset(runtime.project_yaml, "vectors")
-    feature_cfgs = list(dataset.features or [])
-    if include_targets:
-        feature_cfgs += list(dataset.targets or [])
-
-    sanitized = [cfg.model_copy(update={"scale": False})
-                 for cfg in feature_cfgs]
-
-    ids: set[str] = set()
-    context = PipelineContext(runtime)
-    vectors = build_vector_pipeline(
-        context, sanitized, dataset.group_by, stage=None)
-    for _, vector in vectors:
-        ids.update(vector.values.keys())
-    return sorted(ids)
-
-
-def materialize_partitioned_ids(runtime: Runtime, config: BuildConfig) -> Tuple[str, int]:
-    """Write the partitioned-id list and return (relative_path, count)."""
-
-    task_cfg = config.partitioned_ids
-    ids = _collect_partitioned_ids(
-        runtime, include_targets=task_cfg.include_targets)
-
-    relative_path = Path(task_cfg.output)
-    destination = (runtime.artifacts_root / relative_path).resolve()
-    ensure_parent(destination)
-
-    with destination.open("w", encoding="utf-8") as fh:
-        for fid in ids:
-            fh.write(f"{fid}\n")
-
-    return str(relative_path), len(ids)
-
-
-def materialize_scaler_statistics(runtime: Runtime, config: BuildConfig) -> Tuple[str, Dict[str, object]] | None:
-    task_cfg = config.scaler
-    if not task_cfg.enabled:
-        return None
-
-    dataset = load_dataset(runtime.project_yaml, "vectors")
-    feature_cfgs = list(dataset.features)
-    if not feature_cfgs and not task_cfg.include_targets:
-        return None
-
-    if task_cfg.include_targets:
-        feature_cfgs += list(dataset.targets or [])
-
-    sanitized_cfgs = [cfg.model_copy(
-        update={"scale": False}) for cfg in feature_cfgs]
-
-    context = PipelineContext(runtime)
-    vectors = build_vector_pipeline(
-        context, sanitized_cfgs, dataset.group_by, stage=None)
-
-    cfg = getattr(runtime, "split", None)
-    labeler = build_labeler(cfg) if cfg else None
-    if not labeler and task_cfg.split_label != "all":
-        raise RuntimeError(
-            f"Cannot compute scaler statistics for split '{task_cfg.split_label}' "
-            "when no split configuration is defined in the project."
-        )
-
-    def _train_stream() -> Iterator[tuple[object, object]]:
-        for group_key, vector in vectors:
-            if labeler and labeler.label(group_key, vector) != task_cfg.split_label:
-                continue
-            yield group_key, vector
-
-    scaler = StandardScaler()
-    total_observations = scaler.fit(_train_stream())
-
-    if not scaler.statistics:
-        raise RuntimeError(
-            f"No scaler statistics computed for split '{task_cfg.split_label}'."
-        )
-
-    relative_path = Path(task_cfg.output)
-    destination = (runtime.artifacts_root / relative_path).resolve()
-    ensure_parent(destination)
-
-    scaler.save(destination)
-
-    meta: Dict[str, object] = {
-        "features": len(scaler.statistics),
-        "split": task_cfg.split_label,
-        "observations": total_observations,
-    }
-
-    return str(relative_path), meta
-
-
-def execute_build(runtime: Runtime, config: BuildConfig) -> Dict[str, Dict[str, object]]:
-    """Materialize artifacts described by build.yaml."""
-    artifacts: Dict[str, Dict[str, object]] = {}
-
-    rel_path, count = materialize_partitioned_ids(runtime, config)
-    artifacts[PARTIONED_IDS] = {
-        "relative_path": rel_path,
-        "count": count,
-    }
-
-    scaler_result = materialize_scaler_statistics(runtime, config)
-    if scaler_result:
-        rel_path, meta = scaler_result
-        scaler_meta = {"relative_path": rel_path}
-        scaler_meta.update(meta)
-        artifacts[SCALER_STATISTICS] = scaler_meta
-
-    return artifacts

datapipeline/cli/commands/link.py

@@ -1,128 +0,0 @@
-import sys
-from datapipeline.services.paths import pkg_root, resolve_base_pkg_dir
-from datapipeline.services.entrypoints import read_group_entries
-from datapipeline.services.constants import FILTERS_GROUP
-from datapipeline.services.project_paths import (
-    sources_dir as resolve_sources_dir,
-    streams_dir as resolve_streams_dir,
-    ensure_project_scaffold,
-)
-from datapipeline.services.scaffold.mappers import attach_source_to_domain
-import re
-
-
-def _pick_from_list(prompt: str, options: list[str]) -> str:
-    print(prompt, file=sys.stderr)
-    for i, opt in enumerate(options, 1):
-        print(f"  [{i}] {opt}", file=sys.stderr)
-    while True:
-        sel = input("> ").strip()
-        if sel.isdigit():
-            idx = int(sel)
-            if 1 <= idx <= len(options):
-                return options[idx - 1]
-        print("Please enter a number from the list.", file=sys.stderr)
-
-
-def handle() -> None:
-    root_dir, name, pyproject = pkg_root(None)
-
-    # Discover sources by scanning sources_dir YAMLs
-    # Default to dataset-scoped project config
-    proj_path = root_dir / "config" / "datasets" / "default" / "project.yaml"
-    # Ensure a minimal project scaffold so we can resolve dirs interactively
-    ensure_project_scaffold(proj_path)
-    sources_dir = resolve_sources_dir(proj_path)
-    source_options = []
-    if sources_dir.exists():
-        source_options = sorted(p.stem for p in sources_dir.glob("*.y*ml"))
-    if not source_options:
-        print("[error] No sources found. Create one first (jerry source add ...)")
-        raise SystemExit(2)
-
-    src_key = _pick_from_list("Select a source to link:", source_options)
-    # Expect aliases from sources_dir filenames: provider_dataset.yaml
-    parts = src_key.split("_", 1)
-    if len(parts) != 2:
-        print("[error] Source alias must be 'provider_dataset' (from sources/<alias>.yaml)", file=sys.stderr)
-        raise SystemExit(2)
-    provider, dataset = parts[0], parts[1]
-
-    # Discover domains by scanning the package, fallback to EPs if needed
-    base = resolve_base_pkg_dir(root_dir, name)
-    domain_options = []
-    for dirname in ("domains",):
-        dom_dir = base / dirname
-        if dom_dir.exists():
-            domain_options.extend(
-                [p.name for p in dom_dir.iterdir() if p.is_dir()
-                 and (p / "model.py").exists()]
-            )
-    domain_options = sorted(set(domain_options))
-    if not domain_options:
-        domain_options = sorted(
-            read_group_entries(pyproject, FILTERS_GROUP).keys())
-    if not domain_options:
-        print("[error] No domains found. Create one first (jerry domain add ...)")
-        raise SystemExit(2)
-
-    dom_name = _pick_from_list("Select a domain to link to:", domain_options)
-
-    # create mapper + EP (domain.origin)
-    attach_source_to_domain(
-        domain=dom_name,
-        provider=provider,
-        dataset=dataset,
-        root=None,
-    )
-
-    def _slug(s: str) -> str:
-        s = s.strip().lower()
-        s = re.sub(r"[^a-z0-9]+", "_", s)
-        return s.strip("_")
-    ep_key = f"{_slug(dom_name)}.{_slug(provider)}"
-    print(f"[ok] Registered mapper entry point as '{ep_key}'.")
-
-    # Inject per-file canonical stream into streams directory
-    streams_path = resolve_streams_dir(proj_path)
-
-    canonical_alias = ep_key
-    mapper_ep = ep_key
-    # Write a single-file canonical spec into streams directory, matching
-    # ContractConfig schema with helpful commented placeholders per stage.
-    try:
-        # Ensure streams_path is a directory path
-        streams_dir = streams_path if streams_path.is_dir() else streams_path.parent
-        streams_dir.mkdir(parents=True, exist_ok=True)
-        cfile = streams_dir / f"{canonical_alias}.yaml"
-        # Build a richer scaffold as YAML text to preserve comments
-        scaffold = f"""
-source_id: {src_key}
-stream_id: {canonical_alias}
-
-mapper:
-  entrypoint: {mapper_ep}
-  args: {{}}
-
-# partition_by: <field or [fields]> 
-# sort_batch_size: 100000              # in-memory sort chunk size
-
-record:                              # record-level transforms
-  - filter: {{ operator: ge, field: time, comparand: "${{start_time}}" }}
-  - filter: {{ operator: le, field: time, comparand: "${{end_time}}" }}
-#   - floor_time: {{ resolution: 10m }}
-#   - lag: {{ lag: 10m }}
-
-# stream:                              # per-feature transforms (input sorted by id,time)
-#   - ensure_ticks: {{ tick: 10m }}
-#   - granularity: {{ mode: first }}
-#   - fill: {{ statistic: median, window: 6, min_samples: 1 }}
-
-# debug:                               # optional validation-only checks
-#   - lint: {{ mode: warn, tick: 10m }}
-"""
-        with cfile.open("w", encoding="utf-8") as f:
-            f.write(scaffold)
-        print(f"[new] Created canonical spec: {cfile}")
-    except Exception as e:
-        print(f"[error] Failed to write canonical spec: {e}", file=sys.stderr)