{ "id": 3576, "title": "event_popularity_benchmark.csv updated", "url": "/competitions/event-recommendation-engine-challenge/discussion/3576", "author_name": "", "post_date": "2013-01-11T04:43:59.687Z", "votes": null, "comment_count": 3, "views": 1986, "content": "

Just realized the event_popularity_benchmark.csv was an old version of the file that wouldn't get scored properly.

\r\n

I've uploaded a corrected version. If you had trouble submitting this benchmark, download it again and it should work!

", "messages": [ { "id": "19182", "postDate": "01/11/2013 04:43:59", "content": "

Just realized the event_popularity_benchmark.csv was an old version of the file that wouldn't get scored properly.

\r\n

I've uploaded a corrected version. If you had trouble submitting this benchmark, download it again and it should work!

", "rawMarkdown": "", "votes": null }, { "id": "19216", "postDate": "01/12/2013 03:03:56", "content": "

I am having trouble running the benchmark code. I don't have much experience with Python so I am not sure what I am doing wrong. The error is this:

\r\n

Traceback (most recent call last):
\r\nFile "D:\\scott\\kaggle\\events\\pythoncode\\eventpopularitybenchmark.py", line 18, in\r\n
\r\nmain()
\r\nFile "D:\\scott\\kaggle\\events\\pythoncode\\eventpopularitybenchmark.py", line 6, in main
\r\ntrain, test = u.gettraintestdf()
\r\nFile "D:\\scott\\kaggle\\events\\pythoncode\\util.py", line 23, in gettraintestdf
\r\ndatapath, submissionpath = getpaths()
\r\nFile "D:\\scott\\kaggle\\events\\pythoncode\\util.py", line 9, in getpaths
\r\ndata_path = os.path.join(os.environ["d:/scott/kaggle/events/data/"], "EventRecommendation", "Release1")
\r\nFile "C:\\Python27\\lib\\os.py", line 423, in getitem
\r\nreturn self.data[key.upper()]
\r\nKeyError: 'D:/SCOTT/KAGGLE/EVENTS/DATA/'

\r\n

Maybe I don't have the file path in the right format. Something else?

\r\n

My util code looks like this:

\r\n

from dateutil.parser import parse
\r\nimport pandas as pd
\r\nimport os

\r\n

def getpaths():
\r\n"""
\r\nRedefine datapath and submissionspath here to run the benchmarks on your machine
\r\n"""
\r\ndatapath = os.path.join(os.environ["d:/scott/kaggle/events/data/"], "EventRecommendation", "Release1")
\r\nsubmissionpath = os.path.join(os.environ["d:/scott/kaggle/events/data/"], "EventRecommendation", "Submissions")
\r\nreturn datapath, submission_path

\r\n

def getusereventsdict(df):
\r\nuserevents_dict = {user: [] for user in df["user"]}

\r\n
for i, row in df.iterrows():\n    user_events_dict[row["user"]].append(row["event"])    \n\nreturn user_events_dict\n
\r\n

def gettraintestdf(datapath = None):
\r\nif datapath is None:
\r\ndatapath, submissionpath = getpaths()

\r\n
train = pd.read_csv(os.path.join(data_path, "train.csv"),\n    converters={"timestamp": parse})\ntest = pd.read_csv(os.path.join(data_path, "test.csv"),\n    converters={"timestamp": parse})\nreturn train, test\n
\r\n

def geteventattendees(datapath = None):
\r\nif datapath is None:
\r\ndatapath, submissionpath = get_paths()

\r\n
event_attendees_path = os.path.join(data_path, "event_attendees.csv")\nevent_attendees = pd.read_csv(event_attendees_path)\nreturn event_attendees\n
\r\n

def writesubmission(submissionname, usereventsdict, submissionpath=None):
\r\nif submissionpath is None:
\r\ndatapath, submissionpath = get_paths()

\r\n
users = sorted(user_events_dict)\nevents = [user_events_dict[u] for u in users]\n\nsubmission = pd.DataFrame({"User": users, "Events": events})\nsubmission[["User", "Events"]].to_csv(os.path.join(submission_path, submission_name), index=False)\n
\r\n

def geteventresponsesdict(events, respondedusers):
\r\ndef parse_users(u):
\r\nif type(u) == str:
\r\nreturn [int(x) for x in u.split(" ")]
\r\nreturn [u]

\r\n
return {e: parse_users(u) for e, u in zip(events, responded_users)}\n
", "rawMarkdown": "", "votes": null }, { "id": "19253", "postDate": "01/13/2013 06:28:56", "content": "

Where did you get the benchmark code?

", "rawMarkdown": "", "votes": null }, { "id": "19258", "postDate": "01/13/2013 09:46:50", "content": "

Its on Ben's GitHub. https://github.com/benhamner/EventRecommendationChallenge

", "rawMarkdown": "", "votes": null } ], "comments": [ { "id": 19216, "author_name": "alkhwarizmi", "author_url": "", "post_date": "01/12/2013 03:03:56", "content": "

I am having trouble running the benchmark code. I don't have much experience with Python so I am not sure what I am doing wrong. The error is this:

\r\n

Traceback (most recent call last):
\r\nFile "D:\\scott\\kaggle\\events\\pythoncode\\eventpopularitybenchmark.py", line 18, in\r\n
\r\nmain()
\r\nFile "D:\\scott\\kaggle\\events\\pythoncode\\eventpopularitybenchmark.py", line 6, in main
\r\ntrain, test = u.gettraintestdf()
\r\nFile "D:\\scott\\kaggle\\events\\pythoncode\\util.py", line 23, in gettraintestdf
\r\ndatapath, submissionpath = getpaths()
\r\nFile "D:\\scott\\kaggle\\events\\pythoncode\\util.py", line 9, in getpaths
\r\ndata_path = os.path.join(os.environ["d:/scott/kaggle/events/data/"], "EventRecommendation", "Release1")
\r\nFile "C:\\Python27\\lib\\os.py", line 423, in getitem
\r\nreturn self.data[key.upper()]
\r\nKeyError: 'D:/SCOTT/KAGGLE/EVENTS/DATA/'

\r\n

Maybe I don't have the file path in the right format. Something else?

\r\n

My util code looks like this:

\r\n

from dateutil.parser import parse
\r\nimport pandas as pd
\r\nimport os

\r\n

def getpaths():
\r\n"""
\r\nRedefine datapath and submissionspath here to run the benchmarks on your machine
\r\n"""
\r\ndatapath = os.path.join(os.environ["d:/scott/kaggle/events/data/"], "EventRecommendation", "Release1")
\r\nsubmissionpath = os.path.join(os.environ["d:/scott/kaggle/events/data/"], "EventRecommendation", "Submissions")
\r\nreturn datapath, submission_path

\r\n

def getusereventsdict(df):
\r\nuserevents_dict = {user: [] for user in df["user"]}

\r\n
for i, row in df.iterrows():\n    user_events_dict[row["user"]].append(row["event"])    \n\nreturn user_events_dict\n
\r\n

def gettraintestdf(datapath = None):
\r\nif datapath is None:
\r\ndatapath, submissionpath = getpaths()

\r\n
train = pd.read_csv(os.path.join(data_path, "train.csv"),\n    converters={"timestamp": parse})\ntest = pd.read_csv(os.path.join(data_path, "test.csv"),\n    converters={"timestamp": parse})\nreturn train, test\n
\r\n

def geteventattendees(datapath = None):
\r\nif datapath is None:
\r\ndatapath, submissionpath = get_paths()

\r\n
event_attendees_path = os.path.join(data_path, "event_attendees.csv")\nevent_attendees = pd.read_csv(event_attendees_path)\nreturn event_attendees\n
\r\n

def writesubmission(submissionname, usereventsdict, submissionpath=None):
\r\nif submissionpath is None:
\r\ndatapath, submissionpath = get_paths()

\r\n
users = sorted(user_events_dict)\nevents = [user_events_dict[u] for u in users]\n\nsubmission = pd.DataFrame({"User": users, "Events": events})\nsubmission[["User", "Events"]].to_csv(os.path.join(submission_path, submission_name), index=False)\n
\r\n

def geteventresponsesdict(events, respondedusers):
\r\ndef parse_users(u):
\r\nif type(u) == str:
\r\nreturn [int(x) for x in u.split(" ")]
\r\nreturn [u]

\r\n
return {e: parse_users(u) for e, u in zip(events, responded_users)}\n
", "votes": null, "replies": [] }, { "id": 19253, "author_name": "", "author_url": "", "post_date": "01/13/2013 06:28:56", "content": "

Where did you get the benchmark code?

", "votes": null, "replies": [] }, { "id": 19258, "author_name": "brett7", "author_url": "", "post_date": "01/13/2013 09:46:50", "content": "

Its on Ben's GitHub. https://github.com/benhamner/EventRecommendationChallenge

", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "19182": "", "19216": "", "19253": "", "19258": "" }, "source": "meta" }