In this mini-project, you’ll implement an agent that can solve the Sheep and Wolves problem for an arbitrary number of initial wolves and sheep. You will submit the code for solving the problem to the Mini-Project 1 assignment in Gradescope. You will also submit a report describing your agent to Canvas. Your grade will be based on a combination of your report (50%) and your agent’s performance (50%).

About the Project

The Sheep and Wolves problem is identical to the Guards & Prisoners problem from the lecture, except that it makes more semantic sense why the wolves can be alone (they have no sheep to eat). Ignore for a moment the absurdity of wolves needing to outnumber sheep in order to overpower them. Maybe it’s baby wolves vs. adult rams.

As a reminder, the problem goes like this: you are a shepherd tasked with getting sheep and wolves across a river for some reason. If the wolves ever outnumber the sheep on either side of the river, the wolves will overpower and eat the sheep. You have a boat, which can only take one or two animals in it at a time, and must have at least one animal in it because you’ll get lonely (and because the problem is trivial otherwise). How do you move all the animals from one side of the river to the other?

In the original Sheep & Wolves (or Guards & Prisoners) problem, we specified there were 3 sheep and 3 wolves; here, though, your agent should be able to solve the problem for an arbitrary number of initial sheep and wolves. You may assume that the initial state of the problem will follow those rules (e.g. we won’t give you more wolves than sheep to start). However, not every initial state will be solvable; there may be combinations of sheep and wolves that cannot be solved.

You will return a list of moves that will solve the problem, or an empty list if the problem is unsolvable based on the initial set of Sheep and Wolves. You will also submit a brief report describing your approach.

Your Agent

To write your agent, download the starter code below. Complete the solve() method, then upload it to Gradescope to test it against the autograder. Before the deadline, make sure to select your best performance in Gradescope as your submission to be graded.

In this task, you train a sentiment classifier that detects positive and negative sentiment in (English) texts. In machine learning, the choice of learning methods and hyperparameters plays a major role, so you compare different approaches.

Prepare dataset

The “Large Movie Review Dataset” by Maas et al. consists of 50,000 movie reviews from IMDb. Download the dataset (https://ai.stanford.edu/~amaas/data/ sentiment/) and unzip the archive. We are interested in the positive and negative reviews in the training and testing set. Copy the data to the directory structure expected by Scikit-learn:

|– test

• |  |– neg
• |   | |– 0_2.txt
• |   | |– 10000_4.txt
• | | …

o|  `– pos.txt

o|        |– 0_10.txt

o

o|        |– 10000_7.txt

o

o|        …

o`– train

o|– neg

• |  |– 0_3.txt
• |   |– 10000_4.txt
• |  … `– pos
• |–0_9.txt
• |–10000_8.txt
• …

– Train and evaluate models

– Load the training set and the test set.

– Writeafunctionevaluate_pipeline(pipeline, train_set, test_set) that takes a scikit-learn pipeline, a training set, and a test set. The function should train the pipeline on the training set, on the test set with the F1 value

(sklearn.metrics.f1_score) and return it rounded to four decimal places.

Define the following pipelines and train and evaluate them with the

evaluate_pipeline function. Output the evaluation results.

– – Naive Bayes classifier on Tf-Idf values of all words.

– – Naive-Bayes classifier on Tf-Idf values of all words appearing in at least 2 documents.

– Naive Bayes classifier on L2-normalized frequencies of all words.

– – Naive Bayes classifier on L2-normalized frequencies of all words, which occur in at least 2 documents.

– – Linear Support Vector classifier on Tf-Idf values of all words.

– Linear Support Vector classifier on Tf-Idf values of all words occurring in at least 2 documents.

– Linear Support Vector classifier on L2-normalized frequencies of all words.

– Linear Support Vector classifier on L2-normalized frequencies of all words occurring in at least 2 documents.

– Linear Support Vector classifier on Tf-Idf values of all words and word bigrams occurring in at least 2 documents.

– Linear support vector classifier on L2-normalized frequencies of all words and word bigrams occurring in at least 2 documents.

In this project, you will use Software Defined Networking (SDN) principles to create a configurable firewall using an OpenFlow enabled Switch. The Software Defined Networking function allows you to programmatically control the flow of traffic on the network

This project will start with a review of Mininet (this was first used in the optional Simulating Networks project). This review will explain the basic concepts of Mininet and the functionality you may need to complete this project.

The next phase will involve examining network traffic using Wireshark. This will allow you to see the header contents that will be important in building the code necessary to implement the firewall as well as the necessary ruleset you will create to test the firewall.

After this, you will need to perform two tasks that need to be conducted in parallel:

1. You will create a configuration file ruleset that describes certain types of traffic that should be blocked or allowed between individual hosts and networks. You will define this “ruleset” using header packet parameters such as Source IP Address, Destination Port Number, IP Protocol, and Destination MAC Address (there are more parameters, these are given as an example). Your ruleset will contain instruction on whether certain traffic should be blocked or should be allowed. By default, all traffic will be allowed. You will need to specify “routes” that need to be blocked and any specific exceptions to the block that you want to allow.

2. You will create python code that will take the parameters of the configuration from the first task above and create a flow policy object using the POX OpenFlow SDN frameworks. Please start early on this project, especially if you are unfamiliar working with Python APIs.

Part 0: Project References

You will find the following resources useful in completing this project. It is recommended that you review these resources before starting the project.

Project Goals

In this project, you will be developing a simple Java application (processfile) using an agile, test-driven process involving multiple deliverables. While you will receive one grade for the entire project, each deliverable must be completed by its own due date, and all deliverables will contribute to the overall project grade.

Specification of the processfile

Utility processfile is a simple command-line utility written in Java with the following specification:

Summary

processfile allows for simple text manipulation of the content of a file.

Syntax

processfile OPTIONS FILE

Description

Program processfile performs basic text transformations on lines of text from an input FILE. Unless the -f option (see below) is specified, the program writes transformed text to stdout and errors/usage messages to stderr. The FILE parameter is required and must be the last parameter. OPTIONS may be zero or more of the following and may occur in any order:

● -f Edit file in place. The program overwrites the input file with transformed text instead of writing to stdout.

● -n Add line numbers to each line, unpadded starting from 1.

● -s Keep only the lines containing the given string.

● -r Replaces the first instance of string1 in each line with string2.

● -g Used with the -r flag ONLY; replaces all occurrences of string1 in each line with

Project Overview

This project will be built based on the paper Visual Text Correction written by Amir Mazaheri and Mubarak Shah[1]. In this project, given a video clip word description and its corresponding video, our proposed framework will detect the inaccurate word and replace it with a more proper one. The topics such as constructing a more realistic dataset and improving an existing NLP result will be explored and discussed in our project.

Summary of previous work

The foundation of our project is built on the paper written by Amir Mazaheri and Mubarak Shah. In that paper, a system utilizes two modules, the inaccuracy detection module and the correct word prediction module, to find the most inaccurate word in a video description and replace it with a more proper one. The inaccuracy detection module uses a convolutional n-gram network and LSTM to extract the textural information and uses a gating module to extract the visual information. A combination of two makes the prediction of the more inaccurate word. For the correct word prediction module, the system uses text encoding and video encoding to make the prediction for the word.

Potential solutions

Approach 1: Generate a more realistic inaccurate description:

The original false dataset is created only according to the frequency of words and by swapping words with the same part of speech in the sentence. As a result, some extreme unrealistic examples like “swimming in the kitchen” are added to the dataset. Thus, one of our approaches can improve the false dataset by adding more metrics to construct it. We can construct the false dataset by replacing the original word with some words which have a better coherence to the location and movement. In addition, the possible replacement can be built in a tree structure and we can generate the false one from it.

1 Preparation

A Zip archive containing the files for the assignment is provided in Minerva. When you unzip it, you should see three files of earthquake data, along with four .java files. One of these, QuakeException.java, is complete and ready for you to use; the other three files containing empty Java classes.

There are ‘To Do’ comments inside the classes that summarise the code that you need to write, and detailed step-by-step instructions are provided below.

Before you begin programming, take some time to study the sample data. You can use a spreadsheet application to do this. Each row in the dataset represents a single earthquake. The different columns represent various parameters measured for an earthquake. You don’t need to know what most of these are, although further details can be found at the USGS Earthquake Hazards Program website if you are interested. The only columns relevant to this assignment are: latitude, longitude, depth and magnitude.

Note that filenames consist of two parts: a severity level (often expressed in terms of earthquake magnitude) and a time period. The two parts are separated by the underscore character. Thus, 2.5_day.csv contains details of earthquakes of magnitude 2.5 or greater, recorded over a single day; 4.5_week.csv records earthquakes of magnitude 4.5 or greater, over a one-week period; and significant_month.csv records ‘significant’ earthquakes recorded during a one-month period.

2 Quake Class

This class encapsulates the details a single earthquake.

1. Edit Quake.java in a text editor. Add to the class fields that represent the latitude, longitude, depth and magnitude of an earthquake.

2. Create a constructor for Quake that takes a single String parameter. This string represents all of the data provided by the USGS for a single earthquake, with each value separated from the others by commas. To see real examples of what this string looks like, open one of the data files in a text editor (not in a spreadsheet), and examine any of the lines after the first. Note: you can use a method of the String class to help you implement this. Your constructor should perform some basic validation, checking that latitude is within the allowed range of −90.0 ◦ to 90.0 ◦ , and that longitude is within the allowed range of −180.0 ◦ to 180.0 ◦ . You should throw an instance of QuakeException, containing an appropriate error message, if latitude or longitude are invalid.

3. Write simple ‘getter’ methods for each of the fields. These methods should simply return the values of the fields.

4. Write a toString method for Quake. This should generate and return a string representation of the Quake object. The string should contain magnitude, depth, latitude and longitude, in that order, formatted like this example: M5.0, 12.6 km, (35.4975°, 141.0217°) Note: the ‘degrees’ symbol can be generated with the Unicode escape sequence \u00b0. As you complete each step of implementing this class, remove the corresponding ‘To Do’ comment and check that your code compiles. Once you’ve written the constructor and getter methods, you can test them by writing a small program that creates a Quake object from a string. You can use one of the lines from the given data files as the string.