![\"\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F437960%2F5d1f7eec1caeb1006d479ccff185b162%2FAugust.jpg?generation=1572971974803722&alt=media\")
It seems site 14 time zone data is from region around EST but data on both training and weather csv files seems to have GMT timestamps
\n\nAttached plots have plotting for meter reading and air temperature by side ID. Attached is for month of August
It seems site 14 time zone data is from region around EST but data on both training and weather csv files seems to have GMT timestamps
\n\nAttached plots have plotting for meter reading and air temperature by side ID. Attached is for month of August
Based on building data I identified Site 14 as Charlottesville, VA (https://www.kaggle.com/c/ashrae-energy-prediction/discussion/115698). So it is definitely in US/Eastern time zone. \nDo you see such meter readings picture in all buildings in Site 14?
", "rawMarkdown": "Based on building data I identified Site 14 as Charlottesville, VA (https://www.kaggle.com/c/ashrae-energy-prediction/discussion/115698). So it is definitely in US/Eastern time zone. \nDo you see such meter readings picture in all buildings in Site 14?", "votes": null }, { "id": "666849", "postDate": "11/06/2019 15:00:16", "content": "Are you aware that timestamps for weather data and meter data are probably in different time zones (GMT vs local)? It's been discussed a lot and people have guessed out the local timezones of all the sites.
\n\nEdit: I'm not sure why you are bringing up GMT+5. Maybe your timezone conversion logic is backwards? 2000 GMT is 1500 local time zone.
", "rawMarkdown": "Are you aware that timestamps for weather data and meter data are probably in different time zones (GMT vs local)? It's been discussed a lot and people have guessed out the local timezones of all the sites.\n\nEdit: I'm not sure why you are bringing up GMT+5. Maybe your timezone conversion logic is backwards? 2000 GMT is 1500 local time zone.", "votes": null }, { "id": "666956", "postDate": "11/06/2019 16:52:55", "content": "Oddly, the timezone which is 5 hours behind GMT is called ''Etc/GMT+5\", allegedly to match POSIX convention. See description from Wikipedia:\nThe special area of \"Etc\" is used for some administrative zones, particularly for \"Etc/UTC\" which represents Coordinated Universal Time. In order to conform with the POSIX style, those zone names beginning with \"Etc/GMT\" have their sign reversed from the standard ISO 8601 convention. In the \"Etc\" area, zones west of GMT have a positive sign and those east have a negative sign in their name (e.g \"Etc/GMT-14\" is 14 hours ahead of GMT).
", "rawMarkdown": "Oddly, the timezone which is 5 hours behind GMT is called ''Etc/GMT+5\", allegedly to match POSIX convention. See description [from Wikipedia](https://en.wikipedia.org/wiki/Tz_database):\n*The special area of \"Etc\" is used for some administrative zones, particularly for \"Etc/UTC\" which represents Coordinated Universal Time. In order to conform with the POSIX style, those zone names beginning with \"Etc/GMT\" have their sign reversed from the standard ISO 8601 convention. In the \"Etc\" area, zones west of GMT have a positive sign and those east have a negative sign in their name (e.g \"Etc/GMT-14\" is 14 hours ahead of GMT).*", "votes": null }, { "id": "666974", "postDate": "11/06/2019 17:21:19", "content": "I see, thank you.
", "rawMarkdown": "I see, thank you.", "votes": null }, { "id": "670208", "postDate": "11/11/2019 07:09:07", "content": "what i am trying to convey is time data for site 14 buildings in train.csv is in GMT rather than in local time
", "rawMarkdown": "what i am trying to convey is time data for site 14 buildings in train.csv is in GMT rather than in local time", "votes": null }, { "id": "670267", "postDate": "11/11/2019 08:41:21", "content": "I see your point. Usually, energy consumption is small in 0 - 5 am, but it's small in 5 - 10 am on site 14. Site 8 and 10 in the figure are also different in that sense.
", "rawMarkdown": "I see your point. Usually, energy consumption is small in 0 - 5 am, but it's small in 5 - 10 am on site 14. Site 8 and 10 in the figure are also different in that sense.", "votes": null }, { "id": "670288", "postDate": "11/11/2019 09:23:14", "content": "Site 10 is normal if I average log1p(meter_reading). Site 8 is extremely flat (hr independent).
", "rawMarkdown": "Site 10 is normal if I average log1p(meter_reading). Site 8 is extremely flat (hr independent).", "votes": null } ], "comments": [ { "id": 666529, "author_name": "poedator", "author_url": "", "post_date": "11/06/2019 07:28:06", "content": "Based on building data I identified Site 14 as Charlottesville, VA (https://www.kaggle.com/c/ashrae-energy-prediction/discussion/115698). So it is definitely in US/Eastern time zone. \nDo you see such meter readings picture in all buildings in Site 14?
", "votes": null, "replies": [] }, { "id": 666849, "author_name": "sdoria", "author_url": "", "post_date": "11/06/2019 15:00:16", "content": "Are you aware that timestamps for weather data and meter data are probably in different time zones (GMT vs local)? It's been discussed a lot and people have guessed out the local timezones of all the sites.
\n\nEdit: I'm not sure why you are bringing up GMT+5. Maybe your timezone conversion logic is backwards? 2000 GMT is 1500 local time zone.
", "votes": null, "replies": [ { "id": 666956, "author_name": "poedator", "author_url": "", "post_date": "11/06/2019 16:52:55", "content": "Oddly, the timezone which is 5 hours behind GMT is called ''Etc/GMT+5\", allegedly to match POSIX convention. See description from Wikipedia:\nThe special area of \"Etc\" is used for some administrative zones, particularly for \"Etc/UTC\" which represents Coordinated Universal Time. In order to conform with the POSIX style, those zone names beginning with \"Etc/GMT\" have their sign reversed from the standard ISO 8601 convention. In the \"Etc\" area, zones west of GMT have a positive sign and those east have a negative sign in their name (e.g \"Etc/GMT-14\" is 14 hours ahead of GMT).
", "votes": null, "replies": [] }, { "id": 666974, "author_name": "sdoria", "author_url": "", "post_date": "11/06/2019 17:21:19", "content": "I see, thank you.
", "votes": null, "replies": [] }, { "id": 670208, "author_name": "prashant202", "author_url": "", "post_date": "11/11/2019 07:09:07", "content": "what i am trying to convey is time data for site 14 buildings in train.csv is in GMT rather than in local time
", "votes": null, "replies": [] }, { "id": 670267, "author_name": "junkoda", "author_url": "", "post_date": "11/11/2019 08:41:21", "content": "I see your point. Usually, energy consumption is small in 0 - 5 am, but it's small in 5 - 10 am on site 14. Site 8 and 10 in the figure are also different in that sense.
", "votes": null, "replies": [] }, { "id": 670288, "author_name": "junkoda", "author_url": "", "post_date": "11/11/2019 09:23:14", "content": "Site 10 is normal if I average log1p(meter_reading). Site 8 is extremely flat (hr independent).
", "votes": null, "replies": [] } ] } ], "raw_markdown_by_id": { "666022": "It seems site 14 time zone data is from region around EST but data on both training and weather csv files seems to have GMT timestamps\n\n- both meter reading and air temperature are peaking at 2000 hrs\n- normally air temperature should peak around 1500 hrs, indicating both times are GMT+5\n\nAttached plots have plotting for meter reading and air temperature by side ID. Attached is for month of August", "666529": "Based on building data I identified Site 14 as Charlottesville, VA (https://www.kaggle.com/c/ashrae-energy-prediction/discussion/115698). So it is definitely in US/Eastern time zone. \nDo you see such meter readings picture in all buildings in Site 14?", "666849": "Are you aware that timestamps for weather data and meter data are probably in different time zones (GMT vs local)? It's been discussed a lot and people have guessed out the local timezones of all the sites.\n\nEdit: I'm not sure why you are bringing up GMT+5. Maybe your timezone conversion logic is backwards? 2000 GMT is 1500 local time zone.", "666956": "Oddly, the timezone which is 5 hours behind GMT is called ''Etc/GMT+5\", allegedly to match POSIX convention. See description [from Wikipedia](https://en.wikipedia.org/wiki/Tz_database):\n*The special area of \"Etc\" is used for some administrative zones, particularly for \"Etc/UTC\" which represents Coordinated Universal Time. In order to conform with the POSIX style, those zone names beginning with \"Etc/GMT\" have their sign reversed from the standard ISO 8601 convention. In the \"Etc\" area, zones west of GMT have a positive sign and those east have a negative sign in their name (e.g \"Etc/GMT-14\" is 14 hours ahead of GMT).*", "666974": "I see, thank you.", "670208": "what i am trying to convey is time data for site 14 buildings in train.csv is in GMT rather than in local time", "670267": "I see your point. Usually, energy consumption is small in 0 - 5 am, but it's small in 5 - 10 am on site 14. Site 8 and 10 in the figure are also different in that sense.", "670288": "Site 10 is normal if I average log1p(meter_reading). Site 8 is extremely flat (hr independent)." }, "source": "meta" }