Prepping Data For Usage Clustering - machine-learning

Dataset: I'm given the number of minutes individual customers use a product each day and am trying to cluster this data in order to find common usage patterns.
My question: How can I format the data so that, for example, a power user with high levels of use for a year looks the same as a different power user who has only been able to use the device for a month before I ended data collection?
So far I've turned each customer into an array where each cell is the number of minutes used that day. This array starts when the user first uses the product and ends after the user's first year of use. All entries in the cells must be double values (e.x. 200.0 minutes used) for the clustering model. I've considered either setting all cells/days after the last day of data collection to either -1.0 or NULL. Are either of these a valid approach? If not what would you suggest?

For the problem where you want both users (one that used the product a lot every day for a year, and the other used it a lot for one month), create a new entry where it's values are:
avg_usage per time_bin
time_bin can be a month, a day or another time bin which best fits your needs.
This way, a user which use a product, let's say 200 minutes per day for one year, will get:
200 * 30 * 12 / 12 = 6000 minutes per month
and the other user, which joined just last month, will also get, with the exact same usage will get:
200 * 30 * 1 / 1 = 6000 minutes per month.
This way, it doesn't matter when you have started to use the product, the only thing that matter, is the usage rate.
An important thing you might take into consideration, that products, may be forgotten for some time. for example, a computer, and I'm away for a vacation. Those days I didn't use my computer, doesn't have (maybe) an effect of my general usage of this product. So, based on your data, product and intuition you might consider removing gaps like the one I mentioned, and not take it into account inside the calculation.
The amount of time a user has used your product could be a signal of something, but if indeed he only started some time ago, and still using it until today, it may be something you need to take into consideration, and for that use, this average binning technique may help.

Related

What is the time unit for "datadelay" attribute on GoogleFinance?

I'm using the GoogleFinance() functions on a Google spreadsheet to keep track of my stocks. With the "datadelay" attribute I can check how long ago the data has been updated for the last time. But it only returns a raw number, like "54000" for one ticker and "15" for another. What time unit is that supposed to be? minutes? seconds? milliseconds?
When I check the documentation for the Google Finance I saw that there is a page explains there might be delay up to 20 minutes. They also mentioned that they are using different exchanges to retrieve market data and all this different exchanges might have different data delay. It can explain the differences in the "datadelay" column.
For the unit of this column, my assumption is it should be shorter than seconds since 54000 seconds = 900 min, which is far higher than the maximum delay defined in the help page. But I am not sure what would be value for this column when you query in the not-trading days.
The page shows delays for each exchange.
GoogleFinance() function updates every minute (if it is set so), but keep in mind that results may be delayed up to 20 minutes. so the answer is between 1-20 minutes

Change the delay from 20 to 1 minutes

Quotes are not sourced from all markets and may be delayed up to 20
minutes. Information is provided 'as is' and solely for informational
purposes, not for trading purposes or advice.
This advice appears when I use GOOGLEFINANCE() function in my spreadsheet. It is unfortunate that the data is delayed up to 20 minutes.
What is the best way to get real-time stock prices? Suppose my budget is around $50 per month.
Be aware that I trade only US equities, i.e. no bonds, no cryptocurrencies, and so on.
UPDATE
Here is a sample version of my portfolio spreadsheet : https://docs.google.com/spreadsheets/d/1hIfCuupmc_OZ6514DXFe_NrDCX1Ix6tcvySP_VolppI/edit#gid=42667785. It would be important for me to get the price in real-time, and not delayed by maximum 20 minutes.
Is there a way to fix that?
The GOOGLEFINANCE formula is not consistent with the delays. Different stocks can be delayed by different times. You can get an estimate of the delay by using GOOGLEFINANCE("TICKER","DATADELAY").
This is at least somewhat helpful, but not ideal, because you'll have a price on your sheet and you don't know exactly when the price was from, just an estimate of how old the price might be. And forget about pre-market or after-hours. Once the market closes, all bets are off you'll have no idea when the price is from (i.e. after hours quote or regular session close).
If you want accurate real-time quotes, you're going to need an add-on. You said your budget is $50. That doesn't leave you a lot of options. For $9 per month you can use the Market Data Add-on and get real-time stock prices along with historical intraday prices. There is also a free tier that gives you 100 free daily prices.
Market Data's STOCKDATA formula is a drop-in replacement for GOOGLEFINANCE, so it follows the same syntax. It will accomplish what you need. For example, STOCKDATA("SPY","ALL") will produce an output like this:
Date
Bid
Bid Size
Mid
Ask
Ask Size
Last
Volume
5/19/2022 9:09:48
388.36
1400
388.38
388.41
1400
388.37
2715229
Note that the date and time of the quote is included in the output, so you know exactly when the quote was fetched. There is no doubt as to whether the quote is coming from the previous day or whether it is a quote from the pre-market session (which is the case of this example). If you compare to the current time using NOW(), you'll find the Market Data quotes are delayed by about 1-2 seconds, which is due to network latency from your Google Sheet to the servers.
it's important to notice the word "may" in the first sentence:
...and may be delayed up to 20 minutes...
usually, it's way under 20 minutes (around 1 - 1:30 minutes), but there could be times when some delay may occur.
and to answer your question: no, it's not possible to force it under 1 minute
if you want to go full pro mode with Google Sheets then try: =CRYPTOFINANCE()
The documentation links from player0 indicate that ONLY crypto exchanges are supported. Data is NOT available from stock exchanges (NASDAQ, NYSE, etc).

How to calculate the number of consecutive days from Core Data data?

I have some payments(income and expense) which are added to Core Data and every day I calculate the total and also I show how many consecutive days the payments total was positive.
How I am doing right now is always get the total for previous day and increase a counter if its positive. This counter is saved using UserDefaults.
My issue is when lets say the app is deleted and reinstall, the counter is lost, so I am trying to find a way calculate it dynamically every time, but I don't think reading all payments for all days is a good idea in terms of memory.
Another solution is maybe save it using Keychain ?
Is there any other more elegant method? I don't really like the idea of saving this counter.
As an answer
Assuming you reset the counter if the balance goes negative, you just need to load the balance in reverse date order, and count until you go negative?
Depending on how many records you have it may not be performant to read it all in one go. If that's the case read in batches of a manageable size (50 days, perhaps) and only get more data if you are still recording positive balances.
At some point, of course, you may just return "more than 100 days" as a valid response :-)

Handling change of grain for a snapshot fact table in a star-schema

The question
How do you handle a change in grain (from weekly measurement to daily measurement) for a snapshot fact table.
Background info
For a star-schema design I want to incorporate the results of a survey as a fact (e.g. in week 2 of 2015 80% of the respondents have responded 'yes', in week 3 76% etc.)
This survey is conducted each week, and I only have access to the result of the survey (% of people saying yes this week) and not to the individual responses.
Based on (my interpretation of) Christopher Adamson's "Star Schema: The complete reference" I believe I should use a snapshot fact table for these kind of measurements.
The date dimension for this fact should be on the week-level, and be a conformed rollup of a more fine-grained date dimension for other facts in other stars that take place on a daily basis.
Here comes trouble
Now someone decides they want to conduct these surveys daily instead of weekly. What is the best way to handle this? Some of the options I'm currently considering:
change the week dimension to a daily one, and fake the old facts as if they happened on the last day of the week.
change the week dimension to a daily one, and add 7 facts for each weekly one.
create a new star, with the daily fact and dimension and treat the old one as an aggregate.
I'd appreciate any input. Please tell me if my logic is off, or my question is not clear :)
I'm not convinced that this is a snapshot. Each survey response represents a "transaction".
With an appropriate date dimension you can calculate the Yes/No percentages, rolled up by week.
Further, this would enable you to show results like "Surveys issued on a Sunday night get more responses", or "People who respond on Friday are more likely to answer 'Yes'". (contrived examples)
Following clarification, this does look like a periodic snapshot. The example of a bank account balance is often used to describe a similar scenario.
A key feature of a periodic snapshot is that every combination of every dimension should be present. If your grain is monthly, then every month you record the fact, even if it has not changed from the previous month.
I think that is the key to your problem. Knowing that your grain may change from weekly to daily, make your grain daily. It does mean you'll be repeating the weekly value on every day of the week, but that is a true representation of your knowledge of the fact; on Wednesday you only knew that its value was the same as Monday.
If you design your ETL right, you won't need to make any changes when the daily updates begin.
Your second option is the one I'd choose in your place.

Time and date dimension in data warehouse

I'm building a data warehouse. Each fact has it's timestamp. I need to create reports by day, month, quarter but by hours too. Looking at the examples I see that dates tend to be saved in dimension tables.
(source: etl-tools.info)
But I think, that it makes no sense for time. The dimension table would grow and grow. On the other hand JOIN with date dimension table is more efficient than using date/time functions in SQL.
What are your opinions/solutions ?
(I'm using Infobright)
Kimball recommends having separate time- and date dimensions:
design-tip-51-latest-thinking-on-time-dimension-tables
In previous Toolkit books, we have
recommended building such a dimension
with the minutes or seconds component
of time as an offset from midnight of
each day, but we have come to realize
that the resulting end user
applications became too difficult,
especially when trying to compute time
spans. Also, unlike the calendar day
dimension, there are very few
descriptive attributes for the
specific minute or second within a
day. If the enterprise has well
defined attributes for time slices
within a day, such as shift names, or
advertising time slots, an additional
time-of-day dimension can be added to
the design where this dimension is
defined as the number of minutes (or
even seconds) past midnight. Thus this
time-ofday dimension would either have
1440 records if the grain were minutes
or 86,400 records if the grain were
seconds.
My guess is that it depends on your reporting requirement.
If you need need something like
WHERE "Hour" = 10
meaning every day between 10:00:00 and 10:59:59, then I would use the time dimension, because it is faster than
WHERE date_part('hour', TimeStamp) = 10
because the date_part() function will be evaluated for every row.
You should still keep the TimeStamp in the fact table in order to aggregate over boundaries of days, like in:
WHERE TimeStamp between '2010-03-22 23:30' and '2010-03-23 11:15'
which gets awkward when using dimension fields.
Usually, time dimension has a minute resolution, so 1440 rows.
Time should be a dimension on data warehouses, since you will frequently want to aggregate about it. You could use the snowflake-Schema to reduce the overhead. In general, as I pointed out in my comment, hours seem like an unusually high resolution. If you insist on them, making the hour of the day a separate dimension might help, but I cannot tell you if this is good design.
I would recommend having seperate dimension for date and time. Date Dimension would have 1 record for each date as part of identified valid range of dates. For example: 01/01/1980 to 12/31/2025.
And a seperate dimension for time having 86400 records with each second having a record identified by the time key.
In the fact records, where u need date and time both, add both keys having references to these conformed dimensions.

Resources