0

"I'm trying to train NN, but have problems, with text in csv, so I decided to remove all text from it."

"I'm trying to remove text from csv file, but text didn't removes"

TransformProcess tp = new TransformProcess.Builder(schema)
  .removeColumns("MSZoning","Street","Alley","LotConfig","LotShape","LandContour","RoofMatl","LotConfig",
                               "BsmtCond",
                               "Utilities","LandSlope", "Neighborhood", "Condition1", "Condition2", "BldgType",
                               "HouseStyle", "RoofStyle",  "Exterior1st", "Exterior2nd", "MasVnrType", "ExterQual",
                               "ExterCond", "Foundation", "BsmtQual", "BsmtExposure",
                               "BsmtFinType1", "BsmtFinType2", "Heating", "HeatingQC", "CentralAir",  "KitchenQual",
                               "Functional", "FireplaceQu", "GarageType",
                               "GarageFinish", "GarageQual", "GarageCond", "PavedDrive", "PoolQC", "Fence",
                               "MiscFeature", "SaleType", "SaleCondition","Electrical")

csv file

Lemair
  • 51
  • 9

1 Answers1

0

Look at this example: https://github.com/eclipse/deeplearning4j-examples/blob/master/datavec-examples/src/main/java/org/datavec/transform/basic/BasicDataVecExample.java

You need to call tp.build() on your TransformProcess and then get the resulting schema:

Schema outputSchema = tp.getFinalSchema();
reden
  • 968
  • 7
  • 14
  • I have next exception, when transforming categorical to one-hot: "java.lang.IllegalStateException: Cannot convert categorical value to one-hot: input value ("Id") is not in the list of known categories (state names/categories: [A, C, FV, I, RH, RL, RP, RM])" and when something change have instead of 'ID' have number'730'. – Lemair Oct 31 '19 at 12:10