I am studying the example below, which only use rating and movie features, but not user features stored in u.user in the original dataset.
https://docs.fast.ai/tutorial.collab.html
Related
we want to use LUIS to get the entities and intent from a user question and identify the entities that belong to our domain, so what we're doing is training LUIS with a lot of entities that comes from our context domain. Is this a valid and "correct" use of LUIS?
Thanks
Yes you can the intents and entities fro the user question with LUIS. You have to provide training examples accordingly. There are many features in LUIS to label entities which follow a specific pattern using Patterns feature (pattern.any) and provide phrase lists for synonyms. You have to use them based on the scenario. Hope that helps!!
I'm creating a search engine to find in medical documents with a very specific terms. For this I'm training LUIS with this kind of words or tags as "entities".
Yes you are right. The medical term you are referring to are suppose to be entities.
But this approach implies a big bulk of terms in LUIS
If there is a difference only in the term i.e if your utterances are like
search for a
search for b
Then you can add a and b as a phrase list in LUIS, in this way you don't have to keep repeating the utterance for each term. You can check out how to add phrase list. If you look at the 3rd point there you can see that for the name City many city values are being entered. You can do the same with the medical terms you need to search.
In this way you can get the medical terms at your server side by inspecting the entity value.
I am working on KNIME ANALYTIC PLATFORM as part of my project. I am new to this analytics platform.
Prediction Analysis is the practice of extracting information from existing data sets in order to determine patterns and predict future outcomes and trends. ... Knime is based on the Eclipse platform and provides a visual programming language based on data-flows to create an easy-to-understand analysis process quickly
My Approach
With an existing data I was trying to form a pattern. Say like ..
There are several customers with pending amount to be paid and few of them paid. My case was they might exist 1 or more number of orders from customers,
Say customer 1,2 and 3 are there. Cust_1 has 3 orders and Cust_2 has 2 orders and Cust_3 had 1 order, with there some orders amount paid and some not paid.
My Question
My question is can we generate a pattern, based on customers.
To know the customers order more than 2 with coloured and arrange them into pattern? What nodes in knime make my pattern?
can anyone please solve this question.
The patterns in this case what customers buy together, which are expressed as association rules. These rules can applied to new data and can be help predicting new buys by suggesting those products when one of them is in the basket.
In case more information is available on the customers, that can be used to cluster them together based on those properties (which case the patterns are the similarity of the customers) and if a new customer fits in one of those clusters, the most common product(s) can be suggested to her/him/it. The nice thing is that KNIME makes this very easy once you have your data and you get familiar with KNIME (which is itself user friendly, there are many free sources available: https://www.knime.com/resources).
Obviously other patterns might be also useful. If you have more data, you might see trends (patterns) in buys of individual customer orders (or the amount of the orders, where the ARIMA nodes might be useful) or in the popularity of different products. These can also be called patterns.
For complex models, you might need to use other tools too, like R or Python or something else. I should emphasize that KNIME has very good PMML support, so you are not tied to a single tool, you can create/train your model in KNIME and use some other tool to make predictions based on that model or the other way around.
I am new to Shiny and want to make an app for supporting my basic course on Applied Statistics with visualizations based on real data. The idea is that during the first class students (around 75 persons) will enter their own data, including height, weight and sex, which should be stored somewhere in the app and be used in all other sessions for generating plots and calculating statistics.
I have read tutorials and forums but did not find any example that clarifies this issue. Will be very grateful for any hints or links.
I am developing a school management system and I am struggling whether I should develop for [desktop app + wcf] or web app(website). Which one is going to be the best for the given scenario?
The main goals for the “Integrated Web-Based School Management and Quality Audits Software Project for Secondary Schools are outlined below. In addition, specific objectives within each of the goals have been provided.
Goal 1: To facilitate automated data entries in secondary schools
Objective 1:1- To provide internet facilities and computer systems for secondary schools to further facilitate entries of student information into an integrated school management system.
Objective 1:2- To provide teachers with the possibility to enter continuous assessment data into the computer systems for each student.
Objective 1:3- To provide teachers with the possibility to enter end of term results for each student.
Objective 1:4:- To provide teachers with the possibility to enter students’ conduct at end of term for each student
Objective 1:5:- To provide the administration office with the possibility to register new students into the system
Objective 1:6:- To provide finance/fees office with the possibility to enter fees information for each student
Objective 1:7:- To provide parents with the possibility to access their children’s information online and provide feedback when needed or requested to do so
Goal 2:- To generate a portfolio of student information in respect of each student. A unique student identification will be used to access each student’s portfolio. The following are the main components of the portfolio.
Objective 2:1:- One of the components of the students’ portfolio page will be the Result Slip of the immediate last examination term. This will display all subjects taken by the student, continuous assessment results, examination results, grades and positions obtained in each subject, overall student position, student’s conduct and recommendation information. This report will automatically be gathered from the various inputs made from the individual teachers and staff
Objective 2:2:- Up to date historical record of Fees Information. This is vital information that will be available on each student portal. All fees due and all payments made that are entered by the fees/finance staff will be gathered by this component of the portfolio. Parents will be able to see this as well and provide feedback on any observed discrepancies.
Objective 2:3:- Attendance and Conduct report. This component of the portfolio is intended to give an account of the student’s attendance records and information on conduct as provided by the school authorities. If the information demands parent’s attention and feedback, this will be indicated here, and parents will be able to enter relevant feedback as requested.
Objective 2:4:- Completed and Pending Assignments Module. This component of the student’s portfolio will list all assignments completed by the student in the current term and will list uncompleted ones as well.
Goal 3:- To generate aggregated data for the management of the school. This will enable the school management have a high-level overview of student population, performance statistics for all the modules in the various classes, aggregated data on fees paid and fees pending, etc. There will hyperlinks or select options from which authorized staff will click or select from, in order to reach the requested aggregated data. Main components of the management page are listed below,
Objective 3:1:- One of the components of the staff portfolio page will be the Population Statistics. This will indicate total number of students, which is expandable to also list number of males and number of females. This can further be expanded to list female and male students in the various classes
Objective 3:2:- Performance Overview is another component of the staff portfolio. This will provide a high level overview of students’ performance. Per each class and for each subject, this module will list the number of Grade A students, Grade B students and so on and so forth. This links can be further expanded to view the number of males and females who obtained the various grades in the various classes. This module will also compare grades obtained in one subject with another to give an overview of modules that students do very well with those that they do not, to help management take quick action to rectify any anomalies
Objective 3:3:- Fees Overview is another component of the staff portfolio. This will provide fees information in the form of total fees paid within a specific period (Selectable from term, year, previous year(s), all years until current term, etc.). This information can be further expanded to show fees owed per class, payments overdue and allow the fees office to generate generic reminder messages in the form of email or text messages to parents of students who are overdue.
Reading through those requirements, it sounds like this is more than one application.
Undoubtedly you need some sort of web application (probably ASP.NET in some form?) to allow the parents of students to asses their children's records.
However for security purposes this same application should probably not be used for teachers and administrative staff to edit these records. Those functions should be on a protected LAN, and require more application security for viewing or editing any potentially sensitive data (especially financial records).
I don't see where WCF would fit into this, unless you need to provide some web service support to some other system? Or perhaps proving some "application server" on a protected LAN that can use WCF to serve data to 2 separate applications for outside / public access (from separate web servers in a DMZ) and one for internal users.
There isn't really 1 answer to this question.
You said "I am struggling whether I should develop for [desktop app + wcf] or web app(website)", but it sounds like you need to develop the [desktop app + wcf] anyway because the school administration is already using some sort of desktop application to update the data. You also need a web application for the parents to view their children's record. If you can, I strongly suggest you skip the wcf and just do a web application. At my current job, there's something similar to what rally25rs describe, and it is a pain in the ass to maintain the desktop application, the asp.net website and the wcf service business logic. But it sounds like you have no choice, so good luck!
I'm into development of an application that fetches various inputs from internet pages whereas each information snippet comes from a different location (mashup).
I would like to generate the mashup building block (snippets) through a visual tool.
Do you know of anything similar that can be used for such a project? (Already made control, a sample code, article, etc.)
Preferred development environment is .NET - but not mandatory.
IMO the major challenge will be to extract the appropriate information from each feed in semantic form. Wikipedia describes mashups as:
There are many types of mashups, such
as consumer mashups, data mashups, and
enterprise mashups. The most common
type of mashup is the consumer mashup,
aimed at the general public.
Data mashups combine similar types of
media and information from multiple
sources into a single representation.
One example is AlertMap, which
combines data from over 200 sources
related to severe weather conditions,
biohazard threats, and seismic
information, and displays them on a
map of the world; another is Chicago
Crime Map, which indicates the crime
rate and location of crime in Chicago.
The classic mashup - Chicago crime - works because key information such as dates and geolocations are available semantically. Other types of common information are persons, organisations, and domain-specific identifiers.
When you have identified these you may wish to consider the RDF-based tools that the semantic web is developing. Note that governments are starting to emit their data in RDF so I would see this as a key technology
If your web pages do not have semantic information immediately you will probably have to create screen scrapers and HTML parsers. That's not very glamorous, there are no special tools and tends to be just hard work.