Scikit-learn Tutorial - Importing and Exploring

What is Scikit-learn in Python?

Scikit-learn is a free machine-learning library for Python. It’s a very useful tool for data mining and analysis and can be used for personal as well as commercial purposes.

Python Scikit-learn lets users perform various machine learning tasks and provides a means to implement machine learning in Python. It needs to work with Python scientific and numerical libraries, namely, Python SciPy and Python NumPy, respectively. It’s basically a SciPy toolkit that features various machine learning algorithms.

Scikit-learn has small standard datasets that we don’t need to download from any external website. We can just import these datasets directly from Scikit-learn. Following is a list of the datasets that come with Scikit-learn:

1. Boston House Prices Dataset
2. Iris Plants Dataset
3. Diabetes Dataset
4. Digits Dataset
5. Wine Recognition Dataset
6. Breast Cancer Dataset

In this tutorial, we will employ the Iris Plants Dataset with the assistance of Scikit-learn. The dataset comprises parameters such as sepal length, sepal width, petal length, and petal width, which collectively constitute its four fields. Additionally, the dataset incorporates a superclass that encompasses three distinct classes: Iris setosa, Iris versicolor, and Iris virginica. The data within the dataset is organized into three divisions, each corresponding to a distinct species of iris plants represented by these classes.

We will demonstrate how to import this dataset and apply machine learning techniques to it. We can import the same or any of these datasets in the same way as we are following in this tutorial.

Learn more about Python from this Python Data Science Course to get ahead in your career!

Software prerequisites in Scikit-learn in Python:
There are some Python libraries that we will have to install before we can get started with installing Scikit-learn since Scikit-learn is built on these tools in order to support the scientific and numerical libraries of Python. Following are the tools and libraries that we need pre-installed before using Scikit-learn:

• Python (2.7 or above)
• NumPy (1.6.1 or above)
• SciPy (0.9 or above)
• Scikit-learn

Why Python Scikit-learn?

There are not many threads on the Internet where we can actually find the reasons why Scikit-learn has become popular among Data Scientists, but it has some obvious benefits that justify why organizations are using and admiring Scikit-learn. Some of those benefits are listed below.

Benefits of Scikit-learn in Python

• BSD license: Scikit-learn has a BSD license; hence, there is minimal restriction on the use and distribution of the software, making it free to use for everyone.
• Easy to use: The popularity of Scikit-learn is because of its ease of use.
• Document detailing: It also offers document detailing of the API that users can access at any time on the website, helping them integrate Machine Learning into their own platforms.
• Extensive use in the industry: Scikit-learn is used extensively by various organizations to predict consumer behavior, identify suspicious activities, and much more.
• Machine Learning algorithms: Scikit-learn covers most of the machine learning algorithms Huge community support: The ability to perform machine learning tasks using Python has been one of the most significant factors in the growth of Scikit-learn because Python is simple to learn and use (learn Python here), and it already has a large user base, allowing for the performance of machine learning on a platform that is familiar to the user. Being able to perform machine learning tasks using Python has been one of the reasons behind the popularity of Scikit-learn since Python is easy to learn and use (Learn Python here) and already has a huge community of users who can now perform Machine Learning in a platform that they are comfortable with.
• Algorithms flowchart: Unlike other programming languages, where users usually have to choose from multiple competing implementations of the same algorithm, Scikit-learn has an algorithm cheat sheet or flowchart to assist the users

Installation and Configuration

How to Install Scikit-learn?

As we have already seen in the prerequisites section, there is a whole set of other tools and libraries that we need to install before diving into the installation of Scikit-learn. So, let’s start off by discussing the installation of all these libraries, step by step, since the main motivation behind this tutorial is to provide information about Scikit-learn to get started with it.

In case some or all of these libraries are already installed, we can directly jump to the installation of the required library by clicking on it:

• Installing Python
• Installing NumPy
• Installing SciPy
• Installing Scikit learn Python

We will also learn how to use pip to install all these libraries, individually, for those who are not familiar with Python Pip (Pip is a package management system. It is used to manage packages written in Python or with Python dependencies).

Step 1: Installing Python

• We can easily install Python by visiting the following link:

https://www.python.org/downloads/

• Make sure that we install the latest version or at least the version 2.7 or above
• After installing Python, we will need to check if Python is available for us to use on the command line. For that, open the terminal by searching for ‘cmd’ on our system. In the command line, type:

python

If Python is installed successfully, then it should display the Python Version that we are using. This command will open Python Interpreter.

Step 2: Installing NumPy

• NumPy is a fundamental package or library for Python that provides support to perform numerical computations
• Download the installer for NumPy by visiting the following link and then run the installer:

http://sourceforge.net/projects/numpy/files/NumPy/1.10.2/

• We can also install NumPy by running the following command in our terminal:

• pip install numpy

  • If we already have NumPy, then there will be a display, ‘Requirement already satisfied’

Step 3: Installing SciPy

• SciPy is an open-source library for Python to perform scientific computations and technical computations
• Download the SciPy installer using the following link and then run it:

http://sourceforge.net/projects/scipy/files/scipy/0.16.1/

• We can use pip to install SciPy by typing the following command in the terminal:

pip install scipy

• If we already have SciPy, then there will be a display, ‘Requirement already satisfied’

Step 4: Installing Scikit-learn

• Use pip to install Scikit-learn using the following command:

pip install Scikit-learn

• If we already have Scikit Python, then there will be a display, ‘Requirement already satisfied’

import sklearn
import pandas as pd

from sklearn.datasets import load_iris

iriss = load_iris()
df_iris = pd.DataFrame(iriss.data, columns=iriss.feature_names)

df_iris.head()

Now, let’s see how to display the records from the DataFrame using the tail() function:

df_iris.tail()

The tail() function, when used without any argument, displays the last five rows of the data frame. Similar to the head() function, we can pass any integer as an argument to display the same number of records from the end. The output of the above command would be:

Since the tail() function displays the last records of the DataFrame, we can see that the index number of the last row is 149. When we use the head() function, on the other hand, the index number of the first row is 0, i.e., the total number of entries is 150 or a total of 150 records are present in the Iris Plants Dataset.

Interested in learning Python? Enroll in our Python Course in London now!

Now, let’s see how we can check the data types of the fields present in the DataFrame.

df_iris.dtypes

Output:

sepal length (cm) float64
sepal width (cm) float64
petal length (cm) float64
petal width (cm) float64
dtype: object

So, using dtypes, we can list different columns in the DataFrame, along with their respective Python data types.

Data Visualization

Having performed data exploration with our dataset, now let’s create some plots to visually represent the data in our dataset which will help us uncover more stories hidden in it.

Python has many libraries that provide functions to perform data visualizations on datasets. We can use the .plot extension of Pandas to create a scatterplot of features or fields of our dataset against each other, and we also need to import python matplotlib which will provide an object-oriented API to embed plots into applications.

Input:

from pandas.plotting import scatter_matrix
import matplotlib.pyplot as plt
scatter_matrix(df_iris,figsize=(10,10))
plt.show()

Output:

We can also use Seaborn library to create pairplots of all features in the dataset against each other. To use Seaborn, we need to import Seaborn library, first. Let’s see how it is done and how to create a Seaborn pairplot.
Input:

import seaborn as sns
sns.set(style="ticks", color_codes=True)
dfiris = sns.load_dataset("iris")
sns.pairplot(dfiris, hue="species")

We can also use a different color palette, using palette attribute of the pairplot, as shown below:

import seaborn as sns
sns.set(style="ticks", color_codes=True)
dfiris = sns.load_dataset("iris")
sns.pairplot(dfiris, hue="species", palette="husl")

Output:

Learning and Predicting

The scatterplot that we created is useful only to a limited extent. It’s evident that there is a grouping in the species of iris plants into various classes, and it also shows that there are some relationships between the fields or features. But then, it’s hard to point out which class represents which type and which DataPoint represents which flower species in the scatterplot because of the monotone color distribution in the data points.
Luckily, we can rectify and overcome this problem by using the Seaborn module for data visualization in Python. This is exactly what we did by creating a pairplot of the given dataset using Seaborn. We have created two different Seaborn pair plots with two different color palettes. We can refer to any one of them to draw conclusions and predictions, whichever makes it easier for us.

Kick-start your career in Python with the perfect Python Course in New York now!

Selecting Features/Fields:

After being familiar with the data and creating data visualizations, let’s further pick which dataset features or fields we will utilize to perform machine learning and generate predictions. The most sensible features for the machine learning model must be chosen.
Then again, why even choose features? It is reasonable to question why we can’t simply use all features in our machine learning model and let the model choose which feature is the most pertinent to our problem. The solution to this is that not all features have an informational purpose. The model will become needlessly slow and less accurate if features are included merely for the purpose of including data.
Let’s take a better look at them:

It is also noticeable that the boundary between Iris versicolor and Iris virginica seems fuzzy, which might be a problem for some classifiers. We will have to keep that in mind. But, these features still give the most noticeable grouping between the species; hence, we will be using these two features further in our tutorial for our machine learning model.

Preparing Data

Right now, we have the data in Pandas DataFrame. Before we start with the machine learning model, we need to convert the data into NumPy arrays because Ssklearn works well with data in the form of NumPy arrays. It does not work with Pandas DataFrame.This can be done using the following command:

This can be done using the following command:

labels = np.asarray(dfiris.species)

Sklearn comes with a tool, LabelEncoder(), that can encode label strings into numeric representations. It goes through the label and converts the first unique string as 0, then the next as 1, and so on. Let’s see how to use it:

from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
le.fit(labels)
labels = le.transform(labels)

Now, we will remove all features that we don’t need from our DataFrame using the drop() method:

df_selected1 = dfiris.drop(['sepal_length', 'sepal_width', "species"], axis=1)

After this, the only features we are left with are petal length and petal width.

df_features = df_selected1.to_dict(orient='records')
from sklearn.feature_extraction import DictVectorizer
vec = DictVectorizer()
features = vec.fit_transform(df_features).toarray()

from sklearn.model_selection import train_test_split
features_train, features_test, labels_train, labels_test = train_test_split(
features, labels, test_size=0.20, random_state=0)

from sklearn.svm import SVC
svm_model_linear = SVC(kernel = 'linear', C = 1).fit(features_train, labels_train)
svm_predictions = svm_model_linear.predict(features_test)
accuracy = svm_model_linear.score(features_test, labels_test)
print("Test accuracy:",accuracy)

Test accuracy: 1.0

from sklearn.svm import SVC
svm_model_linear = SVC(kernel = 'linear', C = 1).fit(features_train, labels_train)
svm_predictions = svm_model_linear.predict(features_train)
accuracy = svm_model_linear.score(features_train, labels_train)
print(“Train accuracy:”,accuracy)

Train accuracy: 0.9583333333333334

from sklearn.neighbors import KNeighborsClassifier
knn = KNeighborsClassifier(n_neighbors = 7).fit(features_train, labels_train)
accuracy = knn.score(features_test, labels_test)
print(“Test accuracy:” accuracy)

Test accuracy: 1.0

from sklearn.neighbors import KNeighborsClassifier
knn = KNeighborsClassifier(n_neighbors = 7).fit(features_train, labels_train)
accuracy = knn.score(features_train, labels_train)
print(“Train accuracy:” accuracy)

Train accuracy: 0.958