Why does my keras model not train at all?

Question

My code is:

from keras.models import Sequential
from keras.layers import Dense, Dropout, Masking
import numpy as np
import pandas as pd

dataset = pd.read_csv("data/train.csv", header=0)
dataset = dataset.fillna(0)

X = dataset.drop(columns=['YearRemodAdd', "Id", "SalePrice"], axis=1)
Y = dataset[['SalePrice']]

X = pd.get_dummies(X, columns=["MSSubClass", "MSZoning",
                               "Street", "Alley", "LotShape",
                               "LandContour", "Utilities", "LotConfig",
                               "LandSlope", "Neighborhood", "Condition1",
                               "Condition2", "BldgType", "HouseStyle",
                               "YearBuilt", "RoofStyle", "RoofMatl",
                               "Exterior1st", "Exterior2nd", "MasVnrType",
                               "ExterQual", "ExterCond", "Foundation",
                               "BsmtQual", "BsmtCond", "BsmtExposure",
                               "BsmtFinType1", "BsmtFinType2", "Heating",
                               "HeatingQC", "CentralAir", "Electrical",
                               "KitchenQual", "Functional", "FireplaceQu",
                               "GarageType", "GarageFinish", "GarageQual",
                               "GarageCond", "PavedDrive", "PoolQC",
                               "Fence", "MiscFeature", "MoSold",
                               "YrSold", "SaleType", "SaleCondition"])

Ymax = Y['SalePrice'].max()
Y = Y['SalePrice'].apply(lambda x: float(x) / Ymax)

input_units = X.shape[1]
print(X)
print(Y)

model = Sequential()
model.add(Dense(input_units, input_dim=input_units, activation='relu'))
model.add(Dense(input_units, activation='relu'))
model.add(Dense(input_units, activation='relu'))

model.add(Dense(1, activation='sigmoid'))

model.compile(loss='binary_crossentropy',
              optimizer='adam', metrics=['mse'])
model.fit(X, Y, epochs=250, batch_size=50,
          shuffle=True, validation_split=0.05, verbose=2)

scores = model.evaluate(X, Y)
print("\n%s: %.2f%%" % (model.metrics_names[1], scores[1]*100))

My data is like:

Id,MSSubClass,MSZoning,LotFrontage,LotArea,Street,Alley,LotShape,LandContour,Utilities,LotConfig,LandSlope,Neighborhood,Condition1,Condition2,BldgType,HouseStyle,OverallQual,OverallCond,YearBuilt,YearRemodAdd,RoofStyle,RoofMatl,Exterior1st,Exterior2nd,MasVnrType,MasVnrArea,ExterQual,ExterCond,Foundation,BsmtQual,BsmtCond,BsmtExposure,BsmtFinType1,BsmtFinSF1,BsmtFinType2,BsmtFinSF2,BsmtUnfSF,TotalBsmtSF,Heating,HeatingQC,CentralAir,Electrical,1stFlrSF,2ndFlrSF,LowQualFinSF,GrLivArea,BsmtFullBath,BsmtHalfBath,FullBath,HalfBath,BedroomAbvGr,KitchenAbvGr,KitchenQual,TotRmsAbvGrd,Functional,Fireplaces,FireplaceQu,GarageType,GarageYrBlt,GarageFinish,GarageCars,GarageArea,GarageQual,GarageCond,PavedDrive,WoodDeckSF,OpenPorchSF,EnclosedPorch,3SsnPorch,ScreenPorch,PoolArea,PoolQC,Fence,MiscFeature,MiscVal,MoSold,YrSold,SaleType,SaleCondition,SalePrice
1,60,RL,65,8450,Pave,NA,Reg,Lvl,AllPub,Inside,Gtl,CollgCr,Norm,Norm,1Fam,2Story,7,5,2003,2003,Gable,CompShg,VinylSd,VinylSd,BrkFace,196,Gd,TA,PConc,Gd,TA,No,GLQ,706,Unf,0,150,856,GasA,Ex,Y,SBrkr,856,854,0,1710,1,0,2,1,3,1,Gd,8,Typ,0,NA,Attchd,2003,RFn,2,548,TA,TA,Y,0,61,0,0,0,0,NA,NA,NA,0,2,2008,WD,Normal,208500
2,20,RL,80,9600,Pave,NA,Reg,Lvl,AllPub,FR2,Gtl,Veenker,Feedr,Norm,1Fam,1Story,6,8,1976,1976,Gable,CompShg,MetalSd,MetalSd,None,0,TA,TA,CBlock,Gd,TA,Gd,ALQ,978,Unf,0,284,1262,GasA,Ex,Y,SBrkr,1262,0,0,1262,0,1,2,0,3,1,TA,6,Typ,1,TA,Attchd,1976,RFn,2,460,TA,TA,Y,298,0,0,0,0,0,NA,NA,NA,0,5,2007,WD,Normal,181500

My results are:

Epoch 123/250
 - 0s - loss: 3.8653 - mean_squared_error: 0.0687 - val_loss: 3.8064 - val_mean_squared_error: 0.0639
Epoch 124/250

It gets stuck there after like 2 epochs. What can I do to prevent it from getting stuck so quickly?

Answer 1

It seems you are working on a regression problem (i.e. predicting continuous values). There are, at least, two things you need to consider:

1. As @Mitiku has mentioned in the comments section there are some NA (i.e. missing) values in the data. This is one of the reasons that makes the loss to become nan. Either drop the rows which have NA values, or alternatively replace NA values with a specific value such as 0. See this answer for more info about dealing with missing data.

2. Using accuracy as the metric for a regression problem does not make sense as it is only valid for a classification task. Instead use a regression metric such as mse (i.e. mean squared error) or mae (i.e. mean absolute error).

Please apply the two points above in your code, and then report back how the training goes, and I'll update this answer as needed.