{"id":9318,"date":"2020-08-14T06:57:57","date_gmt":"2020-08-14T06:57:57","guid":{"rendered":"https:\/\/www.experfy.com\/blog\/?p=9318"},"modified":"2023-11-20T18:06:18","modified_gmt":"2023-11-20T18:06:18","slug":"how-to-build-a-machine-learning-model","status":"publish","type":"post","link":"https:\/\/www.experfy.com\/blog\/ai-ml\/how-to-build-a-machine-learning-model\/","title":{"rendered":"How to Build a Machine Learning Model"},"content":{"rendered":"\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

\n

A Visual Guide to Learning Data Science<\/h2>\n<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\n

Learning data science may seem intimidating but it doesn\u2019t have to be that way. Let\u2019s make learning data science fun and easy. So the challenge is how do we exactly make learning data science both fun and easy?<\/p>\n\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\n

Cartoons are fun and since \u201ca picture is worth a thousand words\u201d<\/em>, so why not make a cartoon about data science? With that goal in mind, I\u2019ve set out to doodle on my iPad the elements that are required for building a machine learning model. After a few days, the infographic shown above is what I came up with, which was also published on LinkedIn and on the\u00a0Data Professor GitHub<\/a>.<\/p>\n\n\n

\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Dataset<\/h2><\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\n

A dataset is the starting point in your journey of building the machine learning model. Simply put, the dataset is essentially an\u00a0M<\/strong>\u00d7N<\/strong>\u00a0matrix where\u00a0M<\/strong>\u00a0represents the columns (features) and\u00a0N<\/strong>\u00a0the rows (samples).<\/p>\n\n\n\n

Columns can be broken down to\u00a0X<\/strong>\u00a0and\u00a0Y<\/strong>. Firstly,\u00a0X<\/strong>\u00a0is synonymous with several similar terms such as features, independent variables and input variables. Secondly,\u00a0Y<\/strong>\u00a0is also synonymous with several terms namely class label, dependent variable and output variable.<\/p>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\n

It should be noted that a dataset that can be used for\u00a0supervised learning\u00a0<\/em><\/strong>(can perform either regression or classification)would contain both\u00a0X<\/strong>\u00a0and\u00a0Y<\/strong>\u00a0whereas a dataset that can be used for\u00a0unsupervised learning<\/em><\/strong>\u00a0will only have\u00a0X<\/strong>.<\/p>\n\n\n\n

Moreover, if\u00a0Y<\/strong>\u00a0contains quantitative values then the dataset (comprising of\u00a0X<\/strong>\u00a0and\u00a0Y<\/strong>) can be used for\u00a0regression<\/em><\/strong>\u00a0tasks whereas if\u00a0Y<\/strong>\u00a0contains qualitative values then the dataset (comprising of\u00a0X<\/strong>\u00a0and\u00a0Y<\/strong>) can be used for\u00a0classification tasks<\/em><\/strong>.<\/p>\n\n

\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Exploratory Data Analysis<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\n

Exploratory data analysis (EDA) is performed in order to gain a preliminary understanding and allow us to get acquainted with the dataset. In a typical data science project, one of the first things that I would do is\u00a0\u201ceyeballing the data\u201d\u00a0<\/em>byperforming EDA so as to gain a better understanding of the data.<\/p>\n\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t

Three major EDA approaches that I normally use includes:<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\n
    \n
  • Descriptive statistics<\/strong>\u00a0\u2014 Mean, median, mode, standard deviation<\/li>\n
  • Data visualisations<\/strong>\u00a0\u2014 Heat maps (discerning feature intra-correlation), box plot (visualize group differences), scatter plots (visualize correlations between features), principal component analysis (visualize distribution of clusters presented in the dataset), etc.<\/li>\n
  • Data shaping<\/strong>\u00a0\u2014 Pivoting data, grouping data, filtering data, etc.<\/li>\n<\/ul>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
    \n\t\t\t\t\t\t
    \n\t\t\t\t\t
    \n\t\t\t
    \n\t\t\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t\t\t\t\t\n

    For more step-by-step tutorial on performing these\u00a0exploratory data analysis in Python<\/a>, please check out the video I made on the\u00a0Data Professor YouTube channel<\/a>.<\/p>\n\n\n\n