def CV_A_Model_FromSQL(tag, model, vocab1,vocab2,myconfig,nfold=5,downsample=True):
df_all = dfmaker.get_train_dfs(tag,myconfig,downsample)
df_Train, df_Test = dfmaker.GenerateTestTrain(df_all)
#Test with cross-validation:
modelmaker.model_cv(df_Train,model,vocab1,vocab2,nfold,downsample)
def GetDFs(tag,myconfig):
"""Simply return Test and Train Dataframes for a given tag
tag = tag name
myconfig = config file for accessing MySQL database
"""
#Get all data:
df_all = dfmaker.get_train_dfs(tag,myconfig)
#Break into test and train:
df_Train, df_Test = dfmaker.GenerateTestTrain(df_all)
return df_all, df_Train, df_Test
def Train_A_Model(tag, model, vocab1,vocab2,myconfig,downsample=True):
df_all = dfmaker.get_train_dfs(tag,myconfig)
df_Train, df_Test = dfmaker.GenerateTestTrain(df_all)
#Train the actual model:
trained_model,trained_vocab,tagged_vocab = modelmaker.model_trainer(df_Train,model,vocab1,vocab2,downsample)
#Get predictions
result = modelmaker.model_tester(df_Test,trained_model,trained_vocab,tagged_vocab)
return trained_model, trained_vocab, tagged_vocab, result, df_Test
def CV_A_Model_FromSQL(tag,
model,
vocab1,
vocab2,
myconfig,
nfold=5,
downsample=True):
df_all = dfmaker.get_train_dfs(tag, myconfig, downsample)
df_Train, df_Test = dfmaker.GenerateTestTrain(df_all)
#Test with cross-validation:
modelmaker.model_cv(df_Train, model, vocab1, vocab2, nfold, downsample)
def Train_Final_Model(tag, model, vocab1,vocab2,myconfig,downsample=True):
df_all = dfmaker.get_train_dfs(tag,myconfig)
#Check that CV looks fine:
print "Checking CV (nfold=2):"
modelmaker.model_cv(df_all,model,vocab1,vocab2,2,downsample)
#Train the actual model:
print "Training final model:"
trained_model,trained_vocab1,trained_vocab2 = modelmaker.model_trainer(df_all,model,vocab1,vocab2,downsample)
return trained_model, trained_vocab1, trained_vocab2
def Train_Final_Model(tag, model, vocab1, vocab2, myconfig, downsample=True):
df_all = dfmaker.get_train_dfs(tag, myconfig)
#Check that CV looks fine:
print "Checking CV (nfold=2):"
modelmaker.model_cv(df_all, model, vocab1, vocab2, 2, downsample)
#Train the actual model:
print "Training final model:"
trained_model, trained_vocab1, trained_vocab2 = modelmaker.model_trainer(
df_all, model, vocab1, vocab2, downsample)
return trained_model, trained_vocab1, trained_vocab2
def Train_A_Model(tag, model, vocab1, vocab2, myconfig, downsample=True):
df_all = dfmaker.get_train_dfs(tag, myconfig)
df_Train, df_Test = dfmaker.GenerateTestTrain(df_all)
#Train the actual model:
trained_model, trained_vocab, tagged_vocab = modelmaker.model_trainer(
df_Train, model, vocab1, vocab2, downsample)
#Get predictions
result = modelmaker.model_tester(df_Test, trained_model, trained_vocab,
tagged_vocab)
return trained_model, trained_vocab, tagged_vocab, result, df_Test
def CV_A_Model_FromSQL(tag, model, vocab1,vocab2,myconfig,nfold=5,downsample=True):
"""K-fold CV a model for time and performance, calling from MySQL
tag = tag name
model = model object (sklearn) to train to
vocab1 = Body vocab
vocab2 = Tag vocab
myconfig = config file for accessing MySQL database
nfold = number of folds for CV
downsample = force spoiler and non-spoiler sets to have same size
"""
df_all = dfmaker.get_train_dfs(tag,myconfig,downsample)
df_Train, df_Test = dfmaker.GenerateTestTrain(df_all)
#Test with cross-validation:
modelmaker.model_cv(df_Train,model,vocab1,vocab2,nfold,downsample)
def Train_Final_Model(tag, model, vocab1,vocab2,myconfig,downsample=True):
"""Given a tag name, train a model WITH CROSS-VALIDATION
tag = tag name
model = model object (sklearn) to train to
vocab1 = Body vocab
vocab2 = Tag vocab
myconfig = config file for accessing MySQL database
downsample = force spoiler and non-spoiler sets to have same size
"""
df_all = dfmaker.get_train_dfs(tag,myconfig)
#Check that CV looks fine:
print "Checking CV (nfold=2):"
modelmaker.model_cv(df_all,model,vocab1,vocab2,2,downsample)
#Train the actual model:
print "Training final model:"
trained_model,trained_vocab1,trained_vocab2 = modelmaker.model_trainer(df_all,model,vocab1,vocab2,downsample)
return trained_model, trained_vocab1, trained_vocab2
def Train_A_Model(tag, model, vocab1,vocab2,myconfig,downsample=True):
"""Given a tag name, train a model
tag = tag name
model = model object (sklearn) to train to
vocab1 = Body vocab
vocab2 = Tag vocab
myconfig = config file for accessing MySQL database
downsample = force spoiler and non-spoiler sets to have same size
"""
#Get the data and make Test/Train frames:
df_all = dfmaker.get_train_dfs(tag,myconfig)
df_Train, df_Test = dfmaker.GenerateTestTrain(df_all)
#Train the actual model:
trained_model,trained_vocab,tagged_vocab = modelmaker.model_trainer(df_Train,model,vocab1,vocab2,downsample)
#Get predictions
result = modelmaker.model_tester(df_Test,trained_model,trained_vocab,tagged_vocab)
#Return trained model, vocab, prediction:
return trained_model, trained_vocab, tagged_vocab, result, df_Test
def GetDFs(tag, myconfig):
df_all = dfmaker.get_train_dfs(tag, myconfig)
df_Train, df_Test = dfmaker.GenerateTestTrain(df_all)
return df_all, df_Train, df_Test
def GetDFs(tag,myconfig):
df_all = dfmaker.get_train_dfs(tag,myconfig)
df_Train, df_Test = dfmaker.GenerateTestTrain(df_all)
return df_all, df_Train, df_Test
