temporal files used to check that modules run

examples/main_adult.py

@@ -3,14 +3,11 @@ import pandas as pd
 import torch
 from pathlib import Path
 
-# from pytorch_widedeep.utils.data_utils import prepare_data
-# from pytorch_widedeep.models.wide_deep import WideDeep
+from pytorch_widedeep.utils.wide_utils import WideProcessor
+from pytorch_widedeep.utils.deep_utils import DeepProcessor
 
-# from pytorch_widedeep.initializers import Normal, Uniform, XavierNormal, XavierUniform
-# from pytorch_widedeep.lr_schedulers import MultipleLRScheduler, StepLR, MultiStepLR, ReduceLROnPlateau
-# from pytorch_widedeep.optimizers import Adam, SGD, RAdam
-# from pytorch_widedeep.callbacks import EarlyStopping, ModelCheckpoint
-# from pytorch_widedeep.metrics import BinaryAccuracy
+from pytorch_widedeep.models.wide import Wide
+from pytorch_widedeep.models.deep_dense import DeepDense
 
 # use_cuda = torch.cuda.is_available()
 
@@ -26,21 +23,34 @@ if __name__ == '__main__':
     df.drop('income', axis=1, inplace=True)
     df.head()
 
-
-    from pytorch_widedeep.utils.wide_utils import WideProcessor
     wide_cols = ['age_buckets', 'education', 'relationship','workclass','occupation',
         'native_country','gender']
     crossed_cols = [('education', 'occupation'), ('native_country', 'occupation')]
-    prepare_wide = WideProcessor(wide_cols=wide_cols, crossed_cols=crossed_cols)
-    X_wide = prepare_wide.fit_transform(df)
-
-    from pytorch_widedeep.utils.deep_utils import DeepProcessor
     cat_embed_cols = [('education',10), ('relationship',8), ('workclass',10),
         ('occupation',10),('native_country',10)]
     continuous_cols = ["age","hours_per_week"]
+
+    prepare_wide = WideProcessor(wide_cols=wide_cols, crossed_cols=crossed_cols)
+    X_wide = prepare_wide.fit_transform(df)
+
     prepare_deep = DeepProcessor(embed_cols=cat_embed_cols, continuous_cols=continuous_cols)
     X_deep = prepare_deep.fit_transform(df)
 
+    wide = Wide(X_wide.shape[1], 1)
+    pred_wide = wide(torch.tensor(X_wide[:10]))
+
+    deep = DeepDense(
+        hidden_layers=[32,16],
+        dropout=[0.5],
+        deep_column_idx=prepare_deep.deep_column_idx,
+        embed_input=prepare_deep.embeddings_input,
+        continuous_cols=continuous_cols,
+        batchnorm=True,
+        output_dim=1)
+    pred_deep = deep(torch.tensor(X_deep[:10]))
+    pdb.set_trace()
+
+
     # wd_dataset = prepare_data(df,
     #     target=target,
     #     wide_cols=wide_cols,

examples/main_airbnb.py

@@ -4,88 +4,73 @@ import pickle
 import numpy as np
 import pandas as pd
 
-# from torchvision.transforms import ToTensor, Normalize
-# from pytorch_widedeep.initializers import Normal, Uniform, XavierNormal, XavierUniform
-# from pytorch_widedeep.lr_schedulers import MultipleLRScheduler, StepLR, MultiStepLR
-# from pytorch_widedeep.optimizers import MultipleOptimizers, Adam, SGD, RAdam
-# from pytorch_widedeep.callbacks import EarlyStopping, ModelCheckpoint
-# from pytorch_widedeep.metrics import BinaryAccuracy
-# from pytorch_widedeep.utils.data_utils import prepare_data
-# from pytorch_widedeep.models.wide_deep import WideDeep, WideDeepLoader
+from pytorch_widedeep.utils.text_utils import TextProcessor
+from pytorch_widedeep.models.deep_text import DeepText
 
-import pdb
+from pytorch_widedeep.utils.image_utils import ImageProcessor
+from pytorch_widedeep.models.deep_image import DeepImage
 
-from pytorch_widedeep.utils.base_util import DataProcessor
+import pdb
 
 use_cuda = torch.cuda.is_available()
 
 if __name__ == '__main__':
 
-    filepath = 'data/wd_dataset_airbnb.p'
-
-    # if os.path.isfile(filepath):
-    #     wd = pickle.load(open(filepath, "rb"))
-    # else:
-
-    #     df = pd.read_csv('../data/airbnb/tmp_df.csv')
 
-    #     crossed_cols = (['property_type', 'room_type'],)
-    #     already_dummies = [c for c in df.columns if 'amenity' in c] + ['has_house_rules']
-    #     wide_cols = ['is_location_exact', 'property_type', 'room_type', 'host_gender',
-    #     'instant_bookable'] + already_dummies
-    #     cat_embed_cols = [(c, 16) for c in df.columns if 'catg' in c] + \
-    #         [('neighbourhood_cleansed', 64), ('cancellation_policy', 16)]
-    #     continuous_cols = ['latitude', 'longitude', 'security_deposit', 'extra_people']
-    #     already_standard = ['latitude', 'longitude']
-    #     text_col = 'description'
-    #     word_vectors_path = 'data/glove.6B/glove.6B.100d.txt'
-    #     img_col = 'id'
-    #     img_path = 'data/airbnb/property_picture'
-    #     target = 'yield'
-
-    #     wd = prepare_data(df, target, wide_cols, crossed_cols, cat_embed_cols,
-    #         continuous_cols, already_dummies, already_standard, text_col=text_col,
-    #         word_vectors_path=word_vectors_path, img_col=img_col,
-    #         img_path=img_path, filepath='data/wd_dataset_airbnb.p')
-
-    # from pytorch_widedeep.utils.text_utils import TextProcessor
-    # df = pd.read_csv('../data/airbnb/tmp_df.csv')
-    # text_col = 'description'
-    # word_vectors_path = '../data/glove.6B/glove.6B.100d.txt'
-    # text_processor = TextProcessor(word_vectors_path=word_vectors_path)
-    # X_text = text_processor.fit_transform(df, text_col)
-    # new_X = text_processor.transform(df.iloc[:10, :], text_col)
-    # pdb.set_trace()
+    df = pd.read_csv('../data/airbnb/tmp_df.csv')
 
-    from pytorch_widedeep.utils.image_utils import ImageProcessor
+    crossed_cols = (['property_type', 'room_type'],)
+    already_dummies = [c for c in df.columns if 'amenity' in c] + ['has_house_rules']
+    wide_cols = ['is_location_exact', 'property_type', 'room_type', 'host_gender',
+    'instant_bookable'] + already_dummies
+    cat_embed_cols = [(c, 16) for c in df.columns if 'catg' in c] + \
+        [('neighbourhood_cleansed', 64), ('cancellation_policy', 16)]
+    continuous_cols = ['latitude', 'longitude', 'security_deposit', 'extra_people']
+    already_standard = ['latitude', 'longitude']
+    text_col = 'description'
+    word_vectors_path = '../data/glove.6B/glove.6B.100d.txt'
     img_col = 'id'
     img_path = '../data/airbnb/property_picture'
-    df = pd.read_csv('../data/airbnb/tmp_df.csv')
+    target = 'yield'
+
+    text_processor = TextProcessor(word_vectors_path=word_vectors_path)
+    X_text = text_processor.fit_transform(df, text_col)
+
+    deeptext = DeepText(
+        vocab_size=len(text_processor.vocab.itos),
+        hidden_dim=64,
+        n_layers=3,
+        rnn_dropout=0.5,
+        spatial_dropout=0.5,
+        padding_idx=1,
+        output_dim=1,
+        embedding_matrix=text_processor.embedding_matrix
+        )
+
     image_processor = ImageProcessor()
     X_images = image_processor.fit_transform(df, img_col, img_path)
-    new_X = image_processor.transform(df.iloc[:10,:], img_col, img_path)
-    pdb.set_trace()
-
-    model = WideDeep(output_dim=1, wide_dim=wd.wide.shape[1],
-        cat_embed_input = wd.cat_embed_input,
-        cat_embed_encoding_dict=wd.cat_embed_encoding_dict,
-        continuous_cols=wd.continuous_cols,
-        deep_column_idx=wd.deep_column_idx, add_text=True,
-        vocab_size=len(wd.vocab.itos),
-        word_embed_matrix = wd.word_embed_matrix,
-        add_image=True)
-
-    initializers = {'wide': Normal, 'deepdense':Normal, 'deeptext':Normal, 'deepimage':Normal}
-    optimizers = {'wide': Adam, 'deepdense':Adam, 'deeptext':RAdam, 'deepimage':Adam}
-    schedulers = {'wide': StepLR(step_size=5), 'deepdense':StepLR(step_size=5), 'deeptext':MultiStepLR(milestones=[5,8]),
-        'deepimage':MultiStepLR(milestones=[5,8])}
-    mean = [0.406, 0.456, 0.485]  #BGR
-    std =  [0.225, 0.224, 0.229]  #BGR
-    transforms = [ToTensor, Normalize(mean=mean, std=std)]
-    callbacks = [EarlyStopping, ModelCheckpoint(filepath='model_weights/wd_out.pt')]
-
-    model.compile(method='regression', initializers=initializers, optimizers=optimizers,
-        lr_schedulers=schedulers, callbacks=callbacks, transforms=transforms)
-
-    model.fit(X_wide=wd.wide, X_deep=wd.deepdense, X_text=wd.deeptext, X_img=wd.deepimage,
-        target=wd.target, n_epochs=1, batch_size=32, val_split=0.2)
+    deepimage = DeepImage()
+
+    # model = WideDeep(output_dim=1, wide_dim=wd.wide.shape[1],
+    #     cat_embed_input = wd.cat_embed_input,
+    #     cat_embed_encoding_dict=wd.cat_embed_encoding_dict,
+    #     continuous_cols=wd.continuous_cols,
+    #     deep_column_idx=wd.deep_column_idx, add_text=True,
+    #     vocab_size=len(wd.vocab.itos),
+    #     word_embed_matrix = wd.word_embed_matrix,
+    #     add_image=True)
+
+    # initializers = {'wide': Normal, 'deepdense':Normal, 'deeptext':Normal, 'deepimage':Normal}
+    # optimizers = {'wide': Adam, 'deepdense':Adam, 'deeptext':RAdam, 'deepimage':Adam}
+    # schedulers = {'wide': StepLR(step_size=5), 'deepdense':StepLR(step_size=5), 'deeptext':MultiStepLR(milestones=[5,8]),
+    #     'deepimage':MultiStepLR(milestones=[5,8])}
+    # mean = [0.406, 0.456, 0.485]  #BGR
+    # std =  [0.225, 0.224, 0.229]  #BGR
+    # transforms = [ToTensor, Normalize(mean=mean, std=std)]
+    # callbacks = [EarlyStopping, ModelCheckpoint(filepath='model_weights/wd_out.pt')]
+
+    # model.compile(method='regression', initializers=initializers, optimizers=optimizers,
+    #     lr_schedulers=schedulers, callbacks=callbacks, transforms=transforms)
+
+    # model.fit(X_wide=wd.wide, X_deep=wd.deepdense, X_text=wd.deeptext, X_img=wd.deepimage,
+    #     target=wd.target, n_epochs=1, batch_size=32, val_split=0.2)
\ No newline at end of file
\ No newline at end of file