def prepare_training_fastai(train):
data = train.copy()
data[DEFAULT_USER_COL] = data[DEFAULT_USER_COL].astype('str')
data[DEFAULT_ITEM_COL] = data[DEFAULT_ITEM_COL].astype('str')
data = CollabDataBunch.from_df(data,
user_name=DEFAULT_USER_COL,
item_name=DEFAULT_ITEM_COL,
rating_name=DEFAULT_RATING_COL,
valid_pct=0)
return data
def model_training(self, train, seed):
user_emb = self.get_user_emb_size()
buss_emb = self.get_buss_emb_size()
data = CollabDataBunch.from_df(train,
seed=seed,
user_name='user_id',
item_name='business_id',
rating_name='stars_review')
learn = collab_learner(data,
use_nn=True,
emb_szs={
'user_id': user_emb,
'business_id': buss_emb
},
layers=[256, 128],
y_range=(0., 5.))
learn.lr_find()
learn.recorder.plot()
learn.fit_one_cycle(40, 1e-2)
learn.save(self.get_model_name())
learn.show_results(rows=10)
pd.set_option('display.max_columns', None)
business_w = learn.model.embeds[1].weight[1:]
buss_narray = business_w.cpu().data.numpy()
mms_buss = MinMaxScaler()
buss_narray = mms_buss.fit_transform(buss_narray)
buss_ids = list(learn.data.train_ds.x.classes['business_id'][1:])
self.business_df = pd.DataFrame(buss_narray, index=buss_ids)
user_w = learn.model.embeds[0].weight[1:]
user_narray = user_w.cpu().data.numpy()
mms_user = MinMaxScaler()
user_narray = mms_user.fit_transform(user_narray)
user_ids = list(learn.data.train_ds.x.classes['user_id'][1:])
self.user_df = pd.DataFrame(buss_narray, index=buss_ids)
self.learn = learn
return
def model_training(self, train, seed, factors):
print(" Training EmbeddingDotBias Model , it might take a while ..")
data = CollabDataBunch.from_df(train,
seed=seed,
user_name='user_id',
item_name='business_id',
rating_name='stars_review')
learn1 = collab_learner(data,
n_factors=factors,
y_range=(0., 5.),
wd=1e-1)
print("Finding the learning rate.")
print("\n")
learn1.lr_find()
learn1.recorder.plot()
learn1.fit_one_cycle(40, 3e-4)
learn1.save(self.get_model_name())
print(" Exporting the model.")
print("\n")
learn1.export()
print(" Visalizing the results.")
print("\n")
learn1.show_results(rows=10)
pd.set_option('display.max_columns', None)
print("Completed ...")
print("\n")
return learn1
print(
"Total number of ratings are\t{}".format(data.shape[0]),
"Total number of users are\t{}".format(data[USER].nunique()),
"Total number of items are\t{}".format(data[ITEM].nunique()),
sep="\n"
)
#st.subheader("data loaded")
data_train, data_test = python_random_split(data, ratio=0.7)
split =data_train.shape[0], data_test.shape[0]
st.write("Splitting_Ratio:",split)
data = CollabDataBunch.from_df(data_train, seed=42, valid_pct=0.1)
y_range = [0.5,5.5]
st.write(y_range)
factor=N_FACTORS
st.write("No. of factors:",factor)
learn = collab_learner(data, n_factors=factor, y_range=y_range, wd=1e-1)
learn.model
#st.subheader("data loaded")
fit_onecycle=learn.fit_one_cycle(5, 3e-4)
st.write(fit_onecycle)
"""
!git clone https://github.com/SonaliDasgupta/goodbooks-10k
import pandas as pd
!pip install fastai pytorch
ratings_df = pd.read_csv('goodbooks-10k/ratings.csv')
from fastai.collab import CollabDataBunch
from fastai.collab import collab_learner
import torch.optim as optim
from fastai.metrics import exp_rmspe
data = CollabDataBunch.from_df(ratings_df) #no test dataset here
wd = 1e-3
m = collab_learner(data, n_factors = 50, y_range = (1,5), metrics = [exp_rmspe])
#m.opt_fn = optim.Adam(params = m.parameters, lr = 0.5)
#choosing 50 factors as of now, might try with half the size of dataset later
#ratings go from 1 to 5 hence y_range
from fastai.train import lr_find
lr_find(m)
m.recorder.plot_metrics
m.recorder.plot()
m.opt = optim.Adam(params = m.model.parameters(), lr = 0.03)
m.opt.mom = 0.9
m.fit(3, lr = 0.03, wd = 1e-5) #PULL CODE IN SPYDER AND SEE OPTIM WRAPPER USAGE , TRY WITH ADAM LATER AND ALSO WEIGHT DECAY AND MOMENTUM
def prepare_training_fastai(train):
data = train.copy()
data[DEFAULT_USER_COL] = data[DEFAULT_USER_COL].astype('str')
data[DEFAULT_ITEM_COL] = data[DEFAULT_ITEM_COL].astype('str')
data = CollabDataBunch.from_df(data, user_name=DEFAULT_USER_COL, item_name=DEFAULT_ITEM_COL, rating_name=DEFAULT_RATING_COL, valid_pct=0)
return data
N_FACTORS = 40
EPOCHS = 5
ratings = pd.read_csv('./data/ml-100k/ratings.csv')
# split the dataset
train_valid_df, test_df = python_stratified_split(ratings_df,
ratio=0.75,
min_rating=1,
filter_by="item",
col_user=USER,
col_item=ITEM)
data = CollabDataBunch.from_df(train_valid_df,
user_name=USER,
item_name=ITEM,
rating_name=RATING,
valid_pct=0)
# data.show_batch()
"""Now we will create a `collab_learner` for the data, which by default uses
the `EmbeddingDotBias` model. We will be using 40 latent factors. This will
create an embedding for the users and the items that will map each of these
to 40 floats as can be seen below. Note that the embedding parameters are not
predefined, but are learned by the model.
Although ratings can only range from 1-5, we are setting the range of possible
ratings to a range from 0 to 5.5 -- that will allow the model to predict values
around 1 and 5, which improves accuracy. Lastly, we set a value for weight-decay
for regularization."""
learn = collab_learner(data, n_factors=N_FACTORS, y_range=[0, 5.5], wd=1e-1)