This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from gensim.models.doc2vec import TaggedDocument | |
EMBEDDING_DIM = 200 # dimensionality of user representation | |
class TaggedDocumentIterator(object): | |
def __iter__(self): | |
for row in self.df.itertuples(): | |
yield TaggedDocument( | |
words=dict(row._asdict())['all_orders'].split(), | |
tags=[dict(row._asdict())['user_id']]) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
orders.sort_values(by=['user_id','order_number','add_to_cart_order'], | |
inplace=True) | |
orders_by_uid = orders.groupby("user_id") | |
.apply(lambda order: ' '.join(order['product_id'].tolist())) | |
orders_by_uid = pd.DataFrame(orders_by_uid, | |
columns=['all_orders']) | |
orders_by_uid.reset_index(inplace=True) | |
orders_by_uid.user_id = orders_by_uid.user_id.astype(str) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from sklearn.preprocessing import MinMaxScaler | |
mm_scale = MinMaxScaler() | |
# feature_df is the dataframe with customer features | |
feature_df_scale = pd.DataFrame(mm_scale.fit_transform(feature_df), | |
columns=feature_df.columns, | |
index=feature_df.index.values) | |
tsne_doc_features = TSNE(n_components=2, verbose=1, perplexity=30, n_iter=500) | |
tsne_features_doc = tsne_doc_features.fit_transform(feature_df_scale.values) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from sklearn.metrics import silhouette_samples, silhouette_score | |
for space_name, space in {'t-SNE': tsne_results, | |
'original': model.wv.vectors}.items(): | |
for entity in ['department', 'aisle']: | |
s = silhouette_score(space, df_semantic_item[entity], metric="cosine") | |
print(f"Score on {space_name} space for {entity}s is {s:.4}") | |
-------------- |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from sklearn.manifold import TSNE | |
from sklearn.metrics import pairwise_distances | |
# prepare inputs for t-SNE | |
word_vectors = model.wv | |
vocab = list(model.wv.vocab.keys()) | |
item2vector_dict = {arg:model.wv[arg] for arg in vocab} | |
X = pd.DataFrame(item2vector_dict).T.values | |
# perform t-SNE |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def to_product_name(id, columns='product_name'): | |
Return products_csv[products_csv.product_id==id][columns].values.tolist()[0] | |
def most_similar_readable(model, product_id, topn=10): | |
similar_list = [(product_id, 1.0)] + model.wv.most_similar(str(product_id), | |
topn=topn) | |
return pd.DataFrame([( to_product_name(int(id)), int(id), similarity ) for | |
(id, similarity) in similar_list], | |
columns=['product', 'product_id', 'similarity']) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from gensim.models import Word2Vec | |
import multiprocessing as mp | |
WORD_DIM = 200 # dimensionality of the embedding space | |
model = Word2Vec(product_corpus, | |
window=5, | |
size=WORD_DIM, | |
workers=mp.cpu_count() - 2, | |
min_count=100) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
order_ds = orders_csv.merge(order_products_csv, | |
left_on='order_id', | |
right_index=True) | |
# Creating sequences based on transactions | |
order_product_list = order_ds.sort_values( | |
['user_id','order_id','add_to_cart_order']) | |
[['order_id','product_id']].values.tolist() | |
# Each entry of a corpus is one order represented by |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
products.csv | |
| product_id | product_name | aisle_id | department_id | | |
| 1 | Chocolate Sandwich Cookies | 61 | 19 | | |
| 2 | All-Seasons Salt | 104 | 13 | | |
| 3 | Robust Golden Oolong Tea | 94 | 7 | | |
... | |
departments.csv # coarse categorization | |
| department_id | department | | |
| 1 | frozen | |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
config = ddpg.DEFAULT_CONFIG.copy() | |
config["actor_hiddens"] = [512, 512] | |
config["critic_hiddens"] = [512, 512] | |
config["gamma"] = 0.95 | |
config["timesteps_per_iteration"] = 1000 | |
config["target_network_update_freq"] = 5 | |
config["buffer_size"] = 10000 | |
trainer = ddpg.DDPGTrainer(config=config, env=SimpleSupplyChain) | |
for i in range(n_iterations): |
NewerOlder