<b>----------------------------------------------------------------</b> <br>
Fully connected four-layer neural network <br>
Solves a huge number of cases, classification and regression <br>
Fast, robust and very simple to use, <i> this is the way </i> <br>
(As long as python exists this project will exist) <br>
<b>----------------------------------------------------------------</b> <br>
<br>
<br>
#Manual = https://www.mediafire.com/file/xygt3o9zf7iw3id/Manual_Tupa123.pdf <br>
<br>
#Quick Guide = https://www.mediafire.com/file/a0db7fb3lfsxvaj/Guia_Rapido.pdf <br>
<br>
#Excel example data = https://www.mediafire.com/file/o2nzsmnvweh8w1a/ALETAS.xlsx<br>
#Excel example (old version) = https://www.mediafire.com/file/0xmx5quakd21txu/ALETAS.xls <br>
<br>
<br>
<br>
#-----FILE TO MACHINE LEARNING----------------------------- <br>
<br>
import tupa123 as tu <br>
<br>
X = tu.ExcelMatrix('ALETAS.xlsx', 'Plan1', Lineini=2, Columini=1, columnquantity=5, linesquantity=300) <br>
y = tu.ExcelMatrix('ALETAS.xlsx', 'Plan1', Lineini=2, Columini=6, columnquantity=2, linesquantity=300) <br>
<br>
model = tu.nnet4(nn1c=5, nn2c=7, nn3c=5, nn4c=2, namenet='tupa01') <br>
model.Fit_ADAM(X, y) <br>
model.Plotconv() <br>
<br>
input('end') <br>
<br>
#-----FILE TO APPLICATION OF MACHINE LEARNING-------------- <br>
<br>
import tupa123 as tu <br>
<br>
model = tu.nnet4(nn1c=5, nn2c=7, nn3c=5, nn4c=2, namenet='tupa01') <br>
X_new = tu.ExcelMatrix('ALETAS.xlsx', 'Plan1', Lineini=2, Columini=1, columnquantity=5, linesquantity=1000) <br>
y_resposta = tu.ExcelMatrix('ALETAS.xlsx', 'Plan1', Lineini=2, Columini=6, columnquantity=2, linesquantity=1000) <br>
y_pred = model.Predict(X_new) <br>
<br>
tu.Statistics(y_pred, y_resposta) <br>
tu.PlotCorrelation(y_pred, y_resposta) <br>
tu.PlotComparative(y_pred, y_resposta) <br>
input('end') <br>
<br>
Raw data
{
"_id": null,
"home_page": "",
"name": "tupa123",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "artificial-intelligence neural-networks four-layers regression regression-analysis classification-algorithms tupa123 deep-learning machine-learning data-science artificial-neural-network open-source",
"author": "Leandro Schemmer",
"author_email": "leandro.schemmer@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/8a/57/f7e8a88da1d343ca2891d18bbc8b39c57fe0eba3bb2e4b7a9c687d9fdc66/tupa123-1.5.8.tar.gz",
"platform": null,
"description": "<b>----------------------------------------------------------------</b> <br> \r\nFully connected four-layer neural network <br>\r\nSolves a huge number of cases, classification and regression <br>\r\nFast, robust and very simple to use, <i> this is the way </i> <br>\r\n(As long as python exists this project will exist) <br>\r\n<b>----------------------------------------------------------------</b> <br> \r\n<br>\r\n<br>\r\n#Manual = https://www.mediafire.com/file/xygt3o9zf7iw3id/Manual_Tupa123.pdf <br>\r\n<br>\r\n#Quick Guide = https://www.mediafire.com/file/a0db7fb3lfsxvaj/Guia_Rapido.pdf <br>\r\n<br>\r\n#Excel example data = https://www.mediafire.com/file/o2nzsmnvweh8w1a/ALETAS.xlsx<br>\r\n#Excel example (old version) = https://www.mediafire.com/file/0xmx5quakd21txu/ALETAS.xls <br>\r\n<br>\r\n<br>\r\n<br>\r\n#-----FILE TO MACHINE LEARNING----------------------------- <br>\r\n<br>\r\nimport tupa123 as tu <br>\r\n<br>\r\nX = tu.ExcelMatrix('ALETAS.xlsx', 'Plan1', Lineini=2, Columini=1, columnquantity=5, linesquantity=300) <br>\r\ny = tu.ExcelMatrix('ALETAS.xlsx', 'Plan1', Lineini=2, Columini=6, columnquantity=2, linesquantity=300) <br>\r\n<br>\r\nmodel = tu.nnet4(nn1c=5, nn2c=7, nn3c=5, nn4c=2, namenet='tupa01') <br>\r\nmodel.Fit_ADAM(X, y) <br>\r\nmodel.Plotconv() <br>\r\n<br>\r\ninput('end') <br>\r\n<br>\r\n#-----FILE TO APPLICATION OF MACHINE LEARNING-------------- <br>\r\n<br>\r\nimport tupa123 as tu <br>\r\n<br>\r\nmodel = tu.nnet4(nn1c=5, nn2c=7, nn3c=5, nn4c=2, namenet='tupa01') <br>\r\nX_new = tu.ExcelMatrix('ALETAS.xlsx', 'Plan1', Lineini=2, Columini=1, columnquantity=5, linesquantity=1000) <br>\r\ny_resposta = tu.ExcelMatrix('ALETAS.xlsx', 'Plan1', Lineini=2, Columini=6, columnquantity=2, linesquantity=1000) <br>\r\ny_pred = model.Predict(X_new) <br>\r\n<br>\r\ntu.Statistics(y_pred, y_resposta) <br>\r\ntu.PlotCorrelation(y_pred, y_resposta) <br>\r\ntu.PlotComparative(y_pred, y_resposta) <br>\r\ninput('end') <br>\r\n<br>\r\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "fully connected neural network with four layers",
"version": "1.5.8",
"project_urls": null,
"split_keywords": [
"artificial-intelligence",
"neural-networks",
"four-layers",
"regression",
"regression-analysis",
"classification-algorithms",
"tupa123",
"deep-learning",
"machine-learning",
"data-science",
"artificial-neural-network",
"open-source"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "8a57f7e8a88da1d343ca2891d18bbc8b39c57fe0eba3bb2e4b7a9c687d9fdc66",
"md5": "de8029766a10f8818278153104ffbc0e",
"sha256": "6ced812f09b93a63592f566eeff3c59cd459e1b26141500a6d6699ea8e973c61"
},
"downloads": -1,
"filename": "tupa123-1.5.8.tar.gz",
"has_sig": false,
"md5_digest": "de8029766a10f8818278153104ffbc0e",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 74684,
"upload_time": "2023-06-09T13:45:23",
"upload_time_iso_8601": "2023-06-09T13:45:23.169000Z",
"url": "https://files.pythonhosted.org/packages/8a/57/f7e8a88da1d343ca2891d18bbc8b39c57fe0eba3bb2e4b7a9c687d9fdc66/tupa123-1.5.8.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-06-09 13:45:23",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "tupa123"
}
JSON