def main():
parser = argparse.ArgumentParser()
parser.add_argument("--train_file_path",
default="data/train.csv",
help="training file path")
parser.add_argument("--test_file_path",
default="data/test.csv",
help="testing file path")
parser.add_argument("--approach",
default="SVD",
help="Baseline | SVD | SlopeOne | NMF | CoClustering")
parser.add_argument("--output_ranking_file",
default="ranking",
help="output ranking for test")
bsl_options = {'method': 'sgd', 'n_epochs': 20, 'reg_u': 100, 'reg_i': 50}
options = {
"Baseline": BaselineOnly(bsl_options, verbose=True),
"SVD": SVD(verbose=True, n_factors=20, n_epochs=3),
"SlopeOne": SlopeOne(),
"NMF": NMF(),
"CoClustering": CoClustering()
}
args = parser.parse_args()
reader = Reader(line_format='user item rating timestamp', sep='\t')
algo = options[args.approach]
train_data = Dataset.load_from_file(args.train_file_path, reader=reader)
test_data = Dataset.load_from_file(args.test_file_path, reader=reader)
train_set = train_data.build_full_trainset()
test_set = test_data.build_full_trainset().build_testset()
print("training....")
algo.fit(train_set)
print("testing...")
predictions = algo.test(test_set)
accuracy.mae(predictions, verbose=True)
accuracy.rmse(predictions, verbose=True)
### Extra Credit
output_ranking(predictions,
args.output_ranking_file + "_" + args.approach + ".out")
precisions, recalls = precision_recall_at_k(predictions,
k=10,
threshold=2.5)
print("Precision:",
sum(prec for prec in precisions.values()) / len(precisions))
print("Recall:", sum(rec for rec in recalls.values()) / len(recalls))
print("F-measure:", f_measure(precisions, recalls))
print("conversion_rate:", get_conversion_rate(predictions, k=10))
print("ndcg:", get_ndcg(predictions, k_highest_scores=10))
def all_models(_file_path, modelname):
#data = ds.get_data(_file_path, 'data/data_subset.csv', 0.99)
data = ds.get_data(_file_path)
data_surprise = data[['customer_id', 'product_id', 'star_rating']]. \
rename(columns={'customer_id': 'userID', 'product_id': 'itemID', 'star_rating': 'rating'})
reader = Reader(rating_scale=(1.0, 5.0))
df_loaded = Dataset.load_from_df(data_surprise, reader)
#trainset = df_loaded.build_full_trainset()
results_list = []
# features
reviews = data.shape[0]
n_users = data.customer_id.nunique()
n_products = data.product_id.nunique()
mean_rating = data.star_rating.mean()
rating_std = data.star_rating.std()
sparsity = reviews * 100 / (n_users * n_products)
#for model in ['user_user', 'item_item', 'matrix_fact']:
# Perform cross validation
results = model_selection.cross_validate(select_model(
df_loaded, model_selection=modelname),
df_loaded,
measures=['RMSE', 'MAE'],
cv=5,
verbose=False)
# precisions, recalls = precision_recall_at_k(predictions, k=5, threshold=4)
kf = KFold(n_splits=5)
trainset, testset = train_test_split(df_loaded, test_size=.25)
map_k, mar_k = 0, 0
algo = select_model(df_loaded, model_selection=modelname)
#for trainset, testset in trainset.split():
algo.fit(trainset)
predictions = algo.test(testset)
#uid = str(11613707) # raw user id (as in the ratings file). They are **strings**!
#iid = str(302) # raw item id (as in the ratings file). They are **strings**!
# get a prediction for specific users and items.
#pred = algo.predict(uid,verbose=True)
#pred
top_n = rec.get_top_n(predictions, n=30)
#top_n[data_surprise.userID[38745832]]
# top_n = rec.get_top_n(predictions,data_surprise,userID = 11613707)
# pred_SVD_124 = top.get_top_n(predictions,userId = 13545982,data = data)
#top_n.head(15)
# pred_SVD_124
print('Recommendations for the user')
# print('user Id Item Id')
dfo = pd.DataFrame(columns=['UserId', 'ItemId'])
i = 0
for uid, user_ratings in top_n.items():
row = [uid, top_n[uid]]
dfo.loc[i] = row
i = i + 1
#dfo.to_csv('submissionF.csv', index = False)
# print('Recommendations for the user')
#print(uid, [iid for (iid, _) in user_ratings])
precisions, recalls = metrics.precision_recall_at_k(predictions,
k=5,
threshold=4)
# Precision and recall can then be added for all the splits
merge = dfo.merge(data, left_on='UserId', right_on='customer_id')
merge1 = merge[['UserId', 'product_title']]
print(merge1)
map_k += precisions
mar_k += recalls
# Get results & append algorithm name
tmp = pd.DataFrame.from_dict(results).mean(axis=0)
tmp = tmp.append(pd.Series(map_k / 5, index=['map_k']))
tmp = tmp.append(pd.Series(mar_k / 5, index=['mar_k']))
tmp = tmp.append(pd.Series([str(_file_path)], index=['data']))
tmp = tmp.append(pd.Series([str(modelname)], index=['Algorithm']))
# features
tmp = tmp.append(pd.Series(reviews, index=['reviews']))
tmp = tmp.append(pd.Series(n_users, index=['n_users']))
tmp = tmp.append(pd.Series(n_products, index=['n_products']))
tmp = tmp.append(pd.Series(mean_rating, index=['mean_rating']))
tmp = tmp.append(pd.Series(rating_std, index=['std_rating']))
tmp = tmp.append(pd.Series(sparsity, index=['sparsity']))
results_list.append(tmp)
# print(results_list)
results_df = pd.DataFrame(results_list)
# saving the results file to folder
return results_df
def all_models(_file_path, _save_path):
data = ds.get_data(_file_path, 'data/data_subset.csv', 0.99)
data_surprise = data[['customer_id', 'product_id', 'star_rating']]. \
rename(columns={'customer_id': 'userID', 'product_id': 'itemID', 'star_rating': 'rating'})
reader = Reader(rating_scale=(1.0, 5.0))
df_loaded = Dataset.load_from_df(data_surprise, reader)
results_list = []
# features
reviews = data.shape[0]
n_users = data.customer_id.nunique()
n_products = data.product_id.nunique()
mean_rating = data.star_rating.mean()
rating_std = data.star_rating.std()
sparsity = reviews * 100 / (n_users * n_products)
for model in ['user_user', 'item_item', 'matrix_fact']:
# Perform cross validation
results = model_selection.cross_validate(select_model(
df_loaded, model_selection=model),
df_loaded,
measures=['RMSE', 'MAE'],
cv=5,
verbose=False)
# precisions, recalls = precision_recall_at_k(predictions, k=5, threshold=4)
kf = KFold(n_splits=5)
map_k, mar_k = 0, 0
algo = select_model(df_loaded, model_selection=model)
for trainset, testset in kf.split(df_loaded):
algo.fit(trainset)
predictions = algo.test(testset)
precisions, recalls = metrics.precision_recall_at_k(predictions,
k=5,
threshold=4)
# Precision and recall can then be added for all the splits
map_k += precisions
mar_k += recalls
# Get results & append algorithm name
tmp = pd.DataFrame.from_dict(results).mean(axis=0)
tmp = tmp.append(pd.Series(map_k / 5, index=['map_k']))
tmp = tmp.append(pd.Series(mar_k / 5, index=['mar_k']))
tmp = tmp.append(pd.Series([str(_file_path)], index=['data']))
tmp = tmp.append(pd.Series([str(model)], index=['Algorithm']))
# features
tmp = tmp.append(pd.Series(reviews, index=['reviews']))
tmp = tmp.append(pd.Series(n_users, index=['n_users']))
tmp = tmp.append(pd.Series(n_products, index=['n_products']))
tmp = tmp.append(pd.Series(mean_rating, index=['mean_rating']))
tmp = tmp.append(pd.Series(rating_std, index=['std_rating']))
tmp = tmp.append(pd.Series(sparsity, index=['sparsity']))
results_list.append(tmp)
print(results_list)
results_df = pd.DataFrame(results_list)
# saving the results file to folder
if _save_path:
results_df.to_csv(_save_path, mode='a', index=False)
return results_df
dfo = pd.DataFrame(columns=['UserId', 'ItemId'])
i = 0
for uid, user_ratings in top_n.items():
# print('Recommendations for the user')
# st.write('user ID,Item Id')
row = [uid, top_n[uid]]
dfo.loc[i] = row
i = i + 1
#st.write(uid, [iid for (iid, _) in user_ratings])
print('user Id ,Item Id')
print(uid, [iid for (iid, _) in user_ratings])
precisions, recalls = metrics.precision_recall_at_k(predictions,
k=5,
threshold=4)
# Precision and recall can then be added for all the splits
merge = dfo.merge(data, left_on='UserId', right_on='customer_id')
merge1 = merge[['product_title']]
st.write(merge1)
#UserId = '18206299'
#merge2 = customer_recomendation(47781982)
#st.write(merge2)
#url = st.text_input('Enter CustomerID')
#st.write('The Entered Customer Id is', url)
#merge2 =merge1.loc[43173394]
#st.write(merge2)
map_k += precisions