 Run in Google Colab
|
 View on GitHub
|
Homework 7 - Classification¶
In this assignment, we will be applying some basic classification methods to the soccer database (found on canvas). We will first need to import all the libraries required for this guide.
Instructions¶
In this assignment, you will be performing the specified classification methods in Python.
Step 1: Load Data¶
- Load the following attributes from
Player_Attributes:gk_reflexesgk_kickinggk_handling
These values will be used for classification.
Step 2: Classification (Part 1)¶
- Use
gk_reflexesandgk_kicking. - Choose one of the attributes as the target attribute.
- Generate five classes in the target property by reducing the range of values in the target data.
- Split the data into training and testing sets.
- Apply the following methods and print the resulting
accuracy_scorefromsklearn.metrics:- Logistic Regression
- Support Vector Machine (SVM)
- Decision Tree
- K-Nearest Neighbors (KNN)
Step 3: Classification (Part 2)¶
Repeat Step 2, this time using:
gk_kickingandgk_handling
Again, print the corresponding
accuracy_scorefor each classification method.
Step 4: Analysis (Comment in Python file)¶
Answer the following question as a comment in your Python file:
Since this assignment (Classification) and the previous assignment (Regression) are with the same data, can you compare and conclude which technique is yielding best results?
Dataset Overview¶
The dataset covers information about soccer players in sqlite format. This file is located in the Datasets directory of this repository. The file is called fifa_soccer_dataset.sqlite.gz. This is the same file from the previous homework (assignment 4).
If you haven't decompressed the file, you may need to follow the instructions below to decompress it.
IMPORTANT The database is compressed and needs to be decompressed before use. You can do this by running the following command in your terminal on Linux or MacOS:
gunzip Datasets/fifa_soccer_dataset.sqlite.gz
If you are using Windows, you can use the following command in your powershell:
$sourceFile = "$PWD\Datasets\fifa_soccer_dataset.sqlite.gz"
$destinationFile = "$PWD\Datasets\fifa_soccer_dataset.sqlite"
$inputStream = [System.IO.File]::OpenRead($sourceFile)
$outputStream = [System.IO.File]::Create($destinationFile)
$gzipStream = New-Object System.IO.Compression.GzipStream($inputStream, [System.IO.Compression.CompressionMode]::Decompress)
$gzipStream.CopyTo($outputStream)
$gzipStream.Close()
$outputStream.Close()
$inputStream.Close()
Alternatively, you can extract the file using the GUI of your operating system.
Submission Guidelines¶
- Submit your completed notebook as a HTML export, or a PDF file.
To export to HTML, if you are on Jupyter, select File > Export Notebook As > HTML.
If you are on VSCode, you can use the Jupyter: Export to HTML command.
- Open the command palette (Ctrl+Shift+P or Cmd+Shift+P on Mac).
- Search for
Jupyter: Export to HTML. - Save the HTML file to your computer and submit it via Canvas.
- Search for
import pandas as pd
import sqlite3
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
from sklearn.svm import SVC
from sklearn.neighbors import KNeighborsClassifier
To start this assignment, we first need to connect to the sqlite database, do so below.
# Input Code Here
dataset_path = "../../Datasets/fifa_soccer_dataset.sqlite" # Fix your path accordingly
# Your Code Here
Now connected, let's grab required attributes for the scenario from the Player_Attributes(Using gk_reflexes and gk_kicking) table.
player_attr_df = # Your Code Here
player_attr_df.head()
Droping the rows with are having missing values
# Your Code Here
For this classifying, we'll be using the gk_reflexes and gk_kicking. Pull these values into x and y.
x = player_attr_df[['']].values # Your Code Here
y = player_attr_df[['']].values # Your Code Here
the target variable should be reduced to just 5 classes.
____ = pd.cut(y, bins=5, labels=['Class 1', 'Class 2', 'Class 3', 'Class 4', 'Class 5'])
Let's split the data set into test and training sets using the train_test_split() function. We'll want to transform our x variable, which can be done by calling the transform() function.
X_train, X_test, y_train, y_test= # Your Code Here
sc= StandardScaler()
sc.fit(X_train)
X_train_std= sc._(X_train) # Your Code Here
X_test_std= sc._(X_test) # Your Code Here
To preform a logistic regression, we'll use the LogisticRegression() function. This may take a couple moments to run.
lr= _(C=1000.0, random_state=0,max_iter=1000) #Your Code Here
lr.fit(X_train_std, y_train.ravel())
y_pred= lr.predict(X_test_std)
print(f'Accuracy: {accuracy_score(y_test, y_pred)}')
Great! Let's try applying SVM instead. Try using SVC() below, then use the same prediction and output methods as the above cell.
svm= _(kernel='linear', C=1.0, random_state=0, cache_size=7000) # Your Code Here
svm.fit(X_train_std, y_train.ravel())
y_pred = # Your Prediction Code Here
print(f'Accuracy: {accuracy_score(y_test, y_pred)}')
Let's try using a KNeightbors Classifier. We can call the KNeighborsClassifier() function, and supply 2 parameters: n_neighbors=5 and matric='euclidean. Once you run this method, display the accuracy of your model as you did in the above cells.
knn= # Your Code here
#Your Code to fit the model here
y_pred= # Your Prediction Code Here
# Your Accuracy Output Code Here
let's repeat the above steps agian with gk_kicking and gk_handling.
# Your Code Here
Lastly, in the cell below, answer the question: Since this assignment (Classification) and the previous assignment (Regression) are with the same data, can you compare and conclude which technique is yielding best results?
#Your Answer Here