From 810740265727cb9d072ed35541e760e548f8683f Mon Sep 17 00:00:00 2001 From: Daochen Zha Date: Sun, 20 Sep 2020 16:22:56 -0500 Subject: [PATCH] Update README.md Former-commit-id: 3dc11aff6290f472f4765aceecc22bec589b5494 [formerly 885cd9fd8783583e908f0dcf1a6408193ee8bba2] [formerly 70bcb418c58fa5cf5938cf935d282a9070ca0ae9 [formerly 6f1ecc3116009491c0d73382e87da80f5cc833e3]] [formerly 632d2093f172f397369d2b185d17d643ac69822f [formerly 65cf1e39f8e170a69b335592cceebc1da7356b04] [formerly 6da842be90648f069a2fc11270b3c73bfc25804e [formerly 88b7ba05d1057fad0e4acd778ca4cab0ad7dce03]]] [formerly 63ce699b1dfe1f14238bfc30fb0582bca4dd94cd [formerly e401c67b616e2fc9f74fd478835ad8065d73881e] [formerly 1efd82a5a212af224edc39e1bd8568dec242c899 [formerly e6342194c2c1916005853cda017c038787dcd242]] [formerly 0919f2ebc081b482e6c4451baf4ccca650496830 [formerly 68a203c7a65ac7efdb8c2acb6b8633466416946e] [formerly 8d1103ec6e4534ae663c092138f98ca781564fbd [formerly 02e67215099fa83f1dae846684ad65e82d1c1381]]]] [formerly 7c9346966d7a0ec11fb837b89376573f4c49bf65 [formerly fe3d76b3c60a5c5e41403183c24ccab0db3c8b5e] [formerly bbc46f8211ed3f3aa035d1155384c1186955eebe [formerly 8b82c68cb79e0a65eac871327846dd9540def4d8]] [formerly 9022b9e224a46468339620dd5757d39b240d1ed3 [formerly 38580b9aae7bbfdaabe7cdaddb3fb12adcd0e8d0] [formerly fa7c2b15e119332099bad0f60b6d6203ee7793dc [formerly 8b46a19bd768c0b7534dedb30066815bba1d43fe]]] [formerly a8ef6b2f6ce5a239d33b9e6ac2275424cb457613 [formerly 071416a333296d593fbe7866dd10f6a1c368f0d4] [formerly d048b90437971227263e2cd5699169fb6be7191e [formerly be128065fee597a9d24f4a2e1cf2d6e68073143d]] [formerly c770aafdb151ccfff0d523ade40df25f9c8e8930 [formerly 892716760d00db67944f4aba575002e3f9529016] [formerly 01e2f1ef2b4b91720935b231de5a5c7e55e4ecdb [formerly 34a3c5737acc7a5c5a6eb44d718bb987999ea95f]]]]] [formerly 07a0b718c277f9fb1e1ce7f87c08f8f66eb295ad [formerly b47bc41325b2f979261e7a58d4b39727f2ac95d3] [formerly e61955af693e9096668fac1b8e36a8bfc2a95737 [formerly 8dba8ec6fd16b409d814da23036d4ec603af1499]] [formerly 7ae60683e811426775480dd40f98b95db3f355f0 [formerly df01a2f85d0609bf0436b09897ee378fea617f80] [formerly c57e4c4292c80a1792dfd5fb9b903c23492b304e [formerly b8a2bfebbfbd188ac6b5e17eed63e1e398b6df16]]] [formerly b8d0f92f0277279dfd12d43ed0b7afabbe0ed352 [formerly baa0d6d1d0dff9917f1f44cbf9726e85af468439] [formerly 0550bfb88e0722f28b4a8cfde94e5e0aa37044ba [formerly 5bf453557392c0a1bf14a3a56607f4634804962b]] [formerly f03c106fb3706f07a894b58ecfb153fd2797af69 [formerly 8480413a3b7c38726b9fa132986e77ec0994ab8b] [formerly 4cf1e6f5e164107fe6416f5fc4767027be92297d [formerly a3a82ec84690ed38351afbb771be5f798d268cc4]]]] [formerly bf985d9133697f9cdec48ef9f72dbddc49ce98c1 [formerly 65e46f67119404ed74dc3ce4c57d8b992f56b1c7] [formerly 93c431033baa350b0c85de5253fcca4cf4014f73 [formerly c4fe5609203fb56464095ce248a13efe5259f462]] [formerly 9e2ee3b321d5b5726e42d2acbdaa9a961053e153 [formerly 922038002437f9e8920fac11e6084ce31c03ba1a] [formerly 7e1615d943b95be3d1a8052251fdf82fb2067c9d [formerly 27bff5bba5019c70175418df639bf1948a8e99e4]]] [formerly 90084704ea26f5f6df70a3feaddc7dd5e96aff03 [formerly c3efc032456f8b62a83fdeb915eac498ff238fba] [formerly cb4f4ca5498ce2ac101e65facab9e13cbee726f0 [formerly d7cf1a7617a338d32c7fa6abc7eb3f8fa09d185f]] [formerly 45b76f54351d1448c64cff478db1d3f3287b5d81 [formerly 69ee9205dc17b886b8286fd9ec0b649fcf2f1afa] [formerly 3a41a432996415b143d541426dd3a4b37ca7b754 [formerly 9c8e8ad68fc42173b6b485045693a6e617eeb260]]]]]] Former-commit-id: f964876a1d17cc047f54698d2b4e1c8db2b99de7 [formerly 547762d08068f7bc110cf764ac3b5c3a8e034805] [formerly 7b9818cc93fe14212a64d22031fe808e5b46aa0b [formerly d304e7cc881322d61fc1ff9634bd7144111cb043]] [formerly a4fa3fad3735f40dc6b35edf92f7356d3bc2dac8 [formerly d3c9d2540c416c29381f4de8d510bea9f881c20a] [formerly d1275fa452f23cff4efc7a98b44cb36a09832a77 [formerly 0716a9a7394dbd2d6724bc3f9c0cfc040b7da65e]]] [formerly e168bce1be2d42c6a98ff918ecc6ddade5196a42 [formerly bb03a20ed060e366d82cc6b5b13282d9afdeddf9] [formerly 48b2bb7c3ceeacac587356d5f6b5fce4b600b389 [formerly 77a2706c9ae66532bc87fb8438947a6934f20af6]] [formerly 67388b7f18f62f5a147991e59d9614699e70c3ad [formerly c81801b28cdd2205b4d102d93d18f91f28dd4afc] [formerly c4fb0dc9022764bc37a3e96e5ba8d68f134a815a [formerly 66f9b46b5b965bf10c7d6c7d0047076b98d653ac]]]] [formerly fa7398c0a8f96d88fde1c4b3ed1e83b554c049bb [formerly 89d7de72490540d108c791cdac9787e30db60c70] [formerly a4b3d896bf12cc9db3dfd9227863b7789fa2d318 [formerly a42f7a8ebf0cb9251392d8ac45e5fa3a3e6e4678]] [formerly cb3457867d383cbf26cb33d11921f61ffbba1b1f [formerly 66dc161eb4a0ddda1d75781ef7660e63e9dd92c3] [formerly 916b83641bb855a1e969db393a8aa83a8322456e [formerly ea044f3ce10af39e0996e69c2a8f1ba8aec589f9]]] [formerly 6bd59cde6a171609bb0169ec6f2ae4e08465cabd [formerly 4c3603efe185a34e8fe9d7550a785a46cee8603c] [formerly 0d7c78691ae99645d1b2b001eb4bdfb27a0e7b02 [formerly c7bf2527c3d898a6b1000806e5f96976ebaef3d2]] [formerly 6925543571676039da0d104c7ebf4a8c90d0eb50 [formerly 59ed38e4be5a17eb2ed25070b46deaa06318ba10] [formerly 3a41a432996415b143d541426dd3a4b37ca7b754]]]] Former-commit-id: 479cbc7d753ccd697934173b2ce564428f6f411a [formerly 3f60cb47c5617bff5a49446bfca03b9f3d443a27] [formerly 3b6f0bf00061e12fec582a1552cc648ce43913ce [formerly e762b0425805623fe162e69307f1dcdeaf3e9af4]] [formerly 2ebdf6014e188051aa60909e16ed972ec69e2fa7 [formerly 01932fcd00bea4d32feb305eb92f32c29bf1d1a0] [formerly f27b39b2447aec8f9ed7bf24af2b469615eade90 [formerly 7b7254009c308698b2858dfc689e4d6faef2b78b]]] [formerly 4d76f898c33bf86d61fa8dc07c238ead63c6f232 [formerly 8df5ea343dab0dc0869239491acf8a9d8d1c4082] [formerly 103ee9cc55a5f6564aea306218ba4083642c816c [formerly 1fea8556e184f035b163dade6931685622870c15]] [formerly 81cc775b50c110824954702e1f759a2d505d856c [formerly d7cbc21c349dc66acb3ebea524154eb9879211bf] [formerly 97e3a2d1d6ac3144096294681c94a2892668cac7 [formerly 64cd991b893f026681799106dd2e2001b8aaab15]]]] Former-commit-id: 5b47cf1fac4553b13a2f6a275d18a559312d6fe8 [formerly 25afa07d825dbb177615529c9c171cb05b113424] [formerly 950f13ddb9ef4732c9ecd786b7b626998ba01fcb [formerly d308d5fcaabfc48d2b9609ac9f149cca3b4dd8fe]] [formerly 504a5475b4c71eefd02ea67cbda4c4e52edfea4c [formerly 0efed40321bd3a5d38a56631cd4af3a57aded130] [formerly 27059566d23e2e7c57ec639a35994e5d075739d9 [formerly d2fada4f0b54fca824787a5f72790d256549017e]]] Former-commit-id: efc758f343e570696facfda79dede0ad80023515 [formerly e40f37c4a39091f079cf92b236e299f0d27e5927] [formerly 42b370222a9818b5ddae0828fdbeff300375acb4 [formerly 59530c92acd132a9c8b043d50dd09042f12a0c5e]] Former-commit-id: 9eba285d8f645ef6bc122d60742b37e638fc0684 [formerly 30a704f1f7bfa10746208ec0b1ae180f5aebdd4f] Former-commit-id: d0aca01729dbe425529b1bff61dd518553510ef5 --- README.md | 27 +++++++++++---------------- 1 file changed, 11 insertions(+), 16 deletions(-) diff --git a/README.md b/README.md index c3b6b46..3a6b038 100644 --- a/README.md +++ b/README.md @@ -24,24 +24,22 @@ Examples are available in [/examples](examples/). For basic usage, you can evalu import pandas as pd from tods import schemas as schemas_utils -from tods.utils import generate_dataset_problem, evaluate_pipeline +from tods import generate_dataset, evaluate_pipeline table_path = 'datasets/yahoo_sub_5.csv' target_index = 6 # what column is the target -#table_path = 'datasets/NAB/realTweets/labeled_Twitter_volume_IBM.csv' # The path of the dataset -time_limit = 30 # How many seconds you wanna search -#metric = 'F1' # F1 on label 1 metric = 'F1_MACRO' # F1 on both label 0 and 1 -# Read data and generate dataset and problem +# Read data and generate dataset df = pd.read_csv(table_path) -dataset, problem_description = generate_dataset_problem(df, target_index=target_index, metric=metric) +dataset = generate_dataset(df, target_index) # Load the default pipeline pipeline = schemas_utils.load_default_pipeline() # Run the pipeline -pipeline_result = evaluate_pipeline(problem_description, dataset, pipeline) +pipeline_result = evaluate_pipeline(dataset, pipeline, metric) +print(pipeline_result) ``` We also provide AutoML support to help you automatically find a good pipeline for a your data. ```python @@ -49,29 +47,26 @@ import pandas as pd from axolotl.backend.simple import SimpleRunner -from tods.utils import generate_dataset_problem -from tods.search import BruteForceSearch +from tods import generate_dataset, generate_problem +from tods.searcher import BruteForceSearch # Some information -#table_path = 'datasets/NAB/realTweets/labeled_Twitter_volume_GOOG.csv' # The path of the dataset -#target_index = 2 # what column is the target - table_path = 'datasets/yahoo_sub_5.csv' target_index = 6 # what column is the target -#table_path = 'datasets/NAB/realTweets/labeled_Twitter_volume_IBM.csv' # The path of the dataset time_limit = 30 # How many seconds you wanna search -#metric = 'F1' # F1 on label 1 metric = 'F1_MACRO' # F1 on both label 0 and 1 # Read data and generate dataset and problem df = pd.read_csv(table_path) -dataset, problem_description = generate_dataset_problem(df, target_index=target_index, metric=metric) +dataset = generate_dataset(df, target_index=target_index) +problem_description = generate_problem(dataset, metric) # Start backend backend = SimpleRunner(random_seed=0) # Start search algorithm -search = BruteForceSearch(problem_description=problem_description, backend=backend) +search = BruteForceSearch(problem_description=problem_description, + backend=backend) # Find the best pipeline best_runtime, best_pipeline_result = search.search_fit(input_data=[dataset], time_limit=time_limit)