![\"\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F226555%2Fc2511f541f38ef98f6ef43e5623b32ca%2Fbuilding_23.png?generation=1571490839287373&alt=media\")
I've been looking at the electricity consumption of a few series and I noticed that many of them had a very low measure the 4th of June. Here are a few building for which this is the case: 9, 12, 15, 16, 18, 20, 23. I know some people are assuming that the dataset deals with buildings that are in the USA. I also know that the 4th of July (and not June) is a national holiday that side of the sea. I am thus wondering if the data has been \"shifted\" by a month by mistake (or not). Here is the consumption of building 23 to show what I mean:
\n\n
Have any of you noticed the same thing? Maybe I did something wrong when I loaded the data?
", "messages": [ { "id": "652832", "postDate": "10/19/2019 13:18:29", "content": "I've been looking at the electricity consumption of a few series and I noticed that many of them had a very low measure the 4th of June. Here are a few building for which this is the case: 9, 12, 15, 16, 18, 20, 23. I know some people are assuming that the dataset deals with buildings that are in the USA. I also know that the 4th of July (and not June) is a national holiday that side of the sea. I am thus wondering if the data has been \"shifted\" by a month by mistake (or not). Here is the consumption of building 23 to show what I mean:
\n\n
Have any of you noticed the same thing? Maybe I did something wrong when I loaded the data?
", "rawMarkdown": "I've been looking at the electricity consumption of a few series and I noticed that many of them had a very low measure the 4th of June. Here are a few building for which this is the case: 9, 12, 15, 16, 18, 20, 23. I know some people are assuming that the dataset deals with buildings that are in the USA. I also know that the 4th of July (and not June) is a national holiday that side of the sea. I am thus wondering if the data has been \"shifted\" by a month by mistake (or not). Here is the consumption of building 23 to show what I mean:\n\n\n\nHave any of you noticed the same thing? Maybe I did something wrong when I loaded the data?", "votes": null }, { "id": "652846", "postDate": "10/19/2019 13:39:55", "content": "The meter reading is even lower during end of July . But is end of July (or August if there is a month shift) a national holiday there ? There is a list of holiday in this discussion
", "rawMarkdown": "The meter reading is even lower during end of July . But is end of July (or August if there is a month shift) a national holiday there ? There is a list of holiday in this [discussion](https://www.kaggle.com/c/ashrae-energy-prediction/discussion/113286)", "votes": null }, { "id": "652933", "postDate": "10/19/2019 16:33:56", "content": "Just an observation: the buildings from your list are all have the same site_id=0.
Right. So my guess is that each site corresponds to a region of the USA. Even if site_id 0 was not part of the USA, I fail to what the 4th of June corresponds to.
So if all site = 0 - is there a country in the world that anyone knows of that has June 4 as a shut down and party holiday?
", "rawMarkdown": "So if all site = 0 - is there a country in the world that anyone knows of that has June 4 as a shut down and party holiday?", "votes": null }, { "id": "653039", "postDate": "10/19/2019 20:39:05", "content": "I guess that some of the low peaks can be random shutdowns and/or measurement errors. If you look at the series you'll see that some buildings have extremely low electricity consumption on dates that look seemingly random.
", "rawMarkdown": "I guess that some of the low peaks can be random shutdowns and/or measurement errors. If you look at the series you'll see that some buildings have extremely low electricity consumption on dates that look seemingly random.", "votes": null }, { "id": "653055", "postDate": "10/19/2019 21:28:51", "content": "5 min of googling did not bring any positive results. Maybe I should try harder :-). Or maybe this outliers have a completely different meaning. We are assuming that holidays must dramatically affect the power consumption. But then why don't we see any changes in the power consumption during the Christmas time or around the Thanksgiving Day?
", "rawMarkdown": "5 min of googling did not bring any positive results. Maybe I should try harder :-). Or maybe this outliers have a completely different meaning. We are assuming that holidays must dramatically affect the power consumption. But then why don't we see any changes in the power consumption during the Christmas time or around the Thanksgiving Day?", "votes": null }, { "id": "653070", "postDate": "10/19/2019 22:01:00", "content": "For a site (a city) significant power outages can bring down most buildings. Hospitals would have backup generators - not sure if the meter readings would include electric generated by a backup.
\n\nBut if site_id = 0 had most buildings with low usage on Jun 4 than power outage could be the reason.
\n\nSo google - major power outages 2016 ??
", "rawMarkdown": "For a site (a city) significant power outages can bring down most buildings. Hospitals would have backup generators - not sure if the meter readings would include electric generated by a backup.\n\nBut if site_id = 0 had most buildings with low usage on Jun 4 than power outage could be the reason.\n\nSo google - major power outages 2016 ??", "votes": null }, { "id": "653072", "postDate": "10/19/2019 22:05:01", "content": "2016\nOn June 7, Kenya went without power for over 4 hours. The nationwide blackout[173] was caused when a rogue monkey entered a power station. Only about 10 million citizens were affected by the outage as the World Bank estimates that only 23% of the country's population have access to electricity.[174]
\n\nOn Thursday, September 1, Hurricane Hermine swept across the big bend area of Florida, directly affecting the state's capital of Tallahassee. Hermine disrupted power for more than 350,000 people in Florida and southern Georgia, many of whom were without power for a week.
\n\nOn September 21, 2016, a full power system collapse occurred on the island of Puerto Rico affected its 3.5 million inhabitants. The power outage, popularly referred to as the \"Apagón\" (translated as \"super outage\") has been labeled as the largest in Puerto Rico not caused by an atmospheric event. The outage occurred after two transmission lines, with power running up to 230 kV, failed.[175]
\n\nOn September 28, the 2016 South Australian blackout affected the entire state of South Australia (1.7 million people). It was caused by two tornados that destroyed three critical elements of infrastructure, and the power system protected itself by shutting down.[176] While some politicians and commentators have tried to link this power failure with the state's high mix of renewable energy sources (particularly wind energy), some experts have indicated that the blackout had nothing to do with this.[177] A number of technical reports in the previous 18 months expressed concern that the reliability and security of the power supply in South Australia had decreased following the introduction of substantial wind power, and the consequent withdrawal of major conventional power stations.[178]
", "rawMarkdown": "2016\nOn June 7, Kenya went without power for over 4 hours. The nationwide blackout[173] was caused when a rogue monkey entered a power station. Only about 10 million citizens were affected by the outage as the World Bank estimates that only 23% of the country's population have access to electricity.[174]\n\nOn Thursday, September 1, Hurricane Hermine swept across the big bend area of Florida, directly affecting the state's capital of Tallahassee. Hermine disrupted power for more than 350,000 people in Florida and southern Georgia, many of whom were without power for a week.\n\nOn September 21, 2016, a full power system collapse occurred on the island of Puerto Rico affected its 3.5 million inhabitants. The power outage, popularly referred to as the \"Apagón\" (translated as \"super outage\") has been labeled as the largest in Puerto Rico not caused by an atmospheric event. The outage occurred after two transmission lines, with power running up to 230 kV, failed.[175]\n\nOn September 28, the 2016 South Australian blackout affected the entire state of South Australia (1.7 million people). It was caused by two tornados that destroyed three critical elements of infrastructure, and the power system protected itself by shutting down.[176] While some politicians and commentators have tried to link this power failure with the state's high mix of renewable energy sources (particularly wind energy), some experts have indicated that the blackout had nothing to do with this.[177] A number of technical reports in the previous 18 months expressed concern that the reliability and security of the power supply in South Australia had decreased following the introduction of substantial wind power, and the consequent withdrawal of major conventional power stations.[178]", "votes": null }, { "id": "653081", "postDate": "10/19/2019 22:25:09", "content": "Wiki not a very good source - too much monkey business.
\n\nI found a source - will post the link 8 days before the competition ends :)
", "rawMarkdown": "Wiki not a very good source - too much monkey business.\n\nI found a source - will post the link 8 days before the competition ends :)", "votes": null }, { "id": "653084", "postDate": "10/19/2019 22:30:11", "content": "June 4 2016 was not listed as a major outage event in USA by EIA in DOE. Could still be outage but localized. Not sure how big it needs to be before Uncle Sam calls it major.,
", "rawMarkdown": "June 4 2016 was not listed as a major outage event in USA by EIA in DOE. Could still be outage but localized. Not sure how big it needs to be before Uncle Sam calls it major.,", "votes": null }, { "id": "656399", "postDate": "10/24/2019 08:01:11", "content": "doing an hourly temperature analysis, the cycles can be observed. When they do not match it follows that the time zone is different
", "rawMarkdown": "doing an hourly temperature analysis, the cycles can be observed. When they do not match it follows that the time zone is different", "votes": null }, { "id": "658629", "postDate": "10/26/2019 09:29:42", "content": "At least for the weather files, It does not look like it is. More in this notebook:\nhttps://www.kaggle.com/jimeno/ashrae-weather-features-are-not-in-local-time
", "rawMarkdown": "At least for the weather files, It does not look like it is. More in this notebook:\nhttps://www.kaggle.com/jimeno/ashrae-weather-features-are-not-in-local-time", "votes": null } ], "comments": [ { "id": 652846, "author_name": "khairulislam", "author_url": "", "post_date": "10/19/2019 13:39:55", "content": "The meter reading is even lower during end of July . But is end of July (or August if there is a month shift) a national holiday there ? There is a list of holiday in this discussion
", "votes": null, "replies": [ { "id": 653039, "author_name": "maxhalford", "author_url": "", "post_date": "10/19/2019 20:39:05", "content": "I guess that some of the low peaks can be random shutdowns and/or measurement errors. If you look at the series you'll see that some buildings have extremely low electricity consumption on dates that look seemingly random.
", "votes": null, "replies": [] } ] }, { "id": 652933, "author_name": "graf10a", "author_url": "", "post_date": "10/19/2019 16:33:56", "content": "Just an observation: the buildings from your list are all have the same site_id=0.
Right. So my guess is that each site corresponds to a region of the USA. Even if site_id 0 was not part of the USA, I fail to what the 4th of June corresponds to.
So if all site = 0 - is there a country in the world that anyone knows of that has June 4 as a shut down and party holiday?
", "votes": null, "replies": [ { "id": 653055, "author_name": "graf10a", "author_url": "", "post_date": "10/19/2019 21:28:51", "content": "5 min of googling did not bring any positive results. Maybe I should try harder :-). Or maybe this outliers have a completely different meaning. We are assuming that holidays must dramatically affect the power consumption. But then why don't we see any changes in the power consumption during the Christmas time or around the Thanksgiving Day?
", "votes": null, "replies": [] }, { "id": 653070, "author_name": "pcjimmmy", "author_url": "", "post_date": "10/19/2019 22:01:00", "content": "For a site (a city) significant power outages can bring down most buildings. Hospitals would have backup generators - not sure if the meter readings would include electric generated by a backup.
\n\nBut if site_id = 0 had most buildings with low usage on Jun 4 than power outage could be the reason.
\n\nSo google - major power outages 2016 ??
", "votes": null, "replies": [] }, { "id": 653072, "author_name": "pcjimmmy", "author_url": "", "post_date": "10/19/2019 22:05:01", "content": "2016\nOn June 7, Kenya went without power for over 4 hours. The nationwide blackout[173] was caused when a rogue monkey entered a power station. Only about 10 million citizens were affected by the outage as the World Bank estimates that only 23% of the country's population have access to electricity.[174]
\n\nOn Thursday, September 1, Hurricane Hermine swept across the big bend area of Florida, directly affecting the state's capital of Tallahassee. Hermine disrupted power for more than 350,000 people in Florida and southern Georgia, many of whom were without power for a week.
\n\nOn September 21, 2016, a full power system collapse occurred on the island of Puerto Rico affected its 3.5 million inhabitants. The power outage, popularly referred to as the \"Apagón\" (translated as \"super outage\") has been labeled as the largest in Puerto Rico not caused by an atmospheric event. The outage occurred after two transmission lines, with power running up to 230 kV, failed.[175]
\n\nOn September 28, the 2016 South Australian blackout affected the entire state of South Australia (1.7 million people). It was caused by two tornados that destroyed three critical elements of infrastructure, and the power system protected itself by shutting down.[176] While some politicians and commentators have tried to link this power failure with the state's high mix of renewable energy sources (particularly wind energy), some experts have indicated that the blackout had nothing to do with this.[177] A number of technical reports in the previous 18 months expressed concern that the reliability and security of the power supply in South Australia had decreased following the introduction of substantial wind power, and the consequent withdrawal of major conventional power stations.[178]
", "votes": null, "replies": [] }, { "id": 653081, "author_name": "pcjimmmy", "author_url": "", "post_date": "10/19/2019 22:25:09", "content": "Wiki not a very good source - too much monkey business.
\n\nI found a source - will post the link 8 days before the competition ends :)
", "votes": null, "replies": [] }, { "id": 653084, "author_name": "pcjimmmy", "author_url": "", "post_date": "10/19/2019 22:30:11", "content": "June 4 2016 was not listed as a major outage event in USA by EIA in DOE. Could still be outage but localized. Not sure how big it needs to be before Uncle Sam calls it major.,
", "votes": null, "replies": [] } ] }, { "id": 656399, "author_name": "dancaschi", "author_url": "", "post_date": "10/24/2019 08:01:11", "content": "doing an hourly temperature analysis, the cycles can be observed. When they do not match it follows that the time zone is different
", "votes": null, "replies": [] }, { "id": 658629, "author_name": "jimeno", "author_url": "", "post_date": "10/26/2019 09:29:42", "content": "At least for the weather files, It does not look like it is. More in this notebook:\nhttps://www.kaggle.com/jimeno/ashrae-weather-features-are-not-in-local-time
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "652832": "I've been looking at the electricity consumption of a few series and I noticed that many of them had a very low measure the 4th of June. Here are a few building for which this is the case: 9, 12, 15, 16, 18, 20, 23. I know some people are assuming that the dataset deals with buildings that are in the USA. I also know that the 4th of July (and not June) is a national holiday that side of the sea. I am thus wondering if the data has been \"shifted\" by a month by mistake (or not). Here is the consumption of building 23 to show what I mean:\n\n\n\nHave any of you noticed the same thing? Maybe I did something wrong when I loaded the data?", "652846": "The meter reading is even lower during end of July . But is end of July (or August if there is a month shift) a national holiday there ? There is a list of holiday in this [discussion](https://www.kaggle.com/c/ashrae-energy-prediction/discussion/113286)", "652933": "Just an observation: the buildings from your list are all have the same `site_id=0`.", "652964": "Right. So my guess is that each site corresponds to a region of the USA. Even if `site_id` 0 was not part of the USA, I fail to what the 4th of June corresponds to.", "653036": "So if all site = 0 - is there a country in the world that anyone knows of that has June 4 as a shut down and party holiday?", "653039": "I guess that some of the low peaks can be random shutdowns and/or measurement errors. If you look at the series you'll see that some buildings have extremely low electricity consumption on dates that look seemingly random.", "653055": "5 min of googling did not bring any positive results. Maybe I should try harder :-). Or maybe this outliers have a completely different meaning. We are assuming that holidays must dramatically affect the power consumption. But then why don't we see any changes in the power consumption during the Christmas time or around the Thanksgiving Day?", "653070": "For a site (a city) significant power outages can bring down most buildings. Hospitals would have backup generators - not sure if the meter readings would include electric generated by a backup.\n\nBut if site_id = 0 had most buildings with low usage on Jun 4 than power outage could be the reason.\n\nSo google - major power outages 2016 ??", "653072": "2016\nOn June 7, Kenya went without power for over 4 hours. The nationwide blackout[173] was caused when a rogue monkey entered a power station. Only about 10 million citizens were affected by the outage as the World Bank estimates that only 23% of the country's population have access to electricity.[174]\n\nOn Thursday, September 1, Hurricane Hermine swept across the big bend area of Florida, directly affecting the state's capital of Tallahassee. Hermine disrupted power for more than 350,000 people in Florida and southern Georgia, many of whom were without power for a week.\n\nOn September 21, 2016, a full power system collapse occurred on the island of Puerto Rico affected its 3.5 million inhabitants. The power outage, popularly referred to as the \"Apagón\" (translated as \"super outage\") has been labeled as the largest in Puerto Rico not caused by an atmospheric event. The outage occurred after two transmission lines, with power running up to 230 kV, failed.[175]\n\nOn September 28, the 2016 South Australian blackout affected the entire state of South Australia (1.7 million people). It was caused by two tornados that destroyed three critical elements of infrastructure, and the power system protected itself by shutting down.[176] While some politicians and commentators have tried to link this power failure with the state's high mix of renewable energy sources (particularly wind energy), some experts have indicated that the blackout had nothing to do with this.[177] A number of technical reports in the previous 18 months expressed concern that the reliability and security of the power supply in South Australia had decreased following the introduction of substantial wind power, and the consequent withdrawal of major conventional power stations.[178]", "653081": "Wiki not a very good source - too much monkey business.\n\nI found a source - will post the link 8 days before the competition ends :)", "653084": "June 4 2016 was not listed as a major outage event in USA by EIA in DOE. Could still be outage but localized. Not sure how big it needs to be before Uncle Sam calls it major.,", "656399": "doing an hourly temperature analysis, the cycles can be observed. When they do not match it follows that the time zone is different", "658629": "At least for the weather files, It does not look like it is. More in this notebook:\nhttps://www.kaggle.com/jimeno/ashrae-weather-features-are-not-in-local-time" }, "source": "meta" }