{"id":46765,"date":"2023-06-21T00:00:00","date_gmt":"2023-06-21T07:00:00","guid":{"rendered":"https:\/\/griddb-linux-hte8hndjf8cka8ht.westus-01.azurewebsites.net\/blog\/predicting-flight-delays-using-python-and-griddb\/"},"modified":"2025-11-13T12:56:38","modified_gmt":"2025-11-13T20:56:38","slug":"predicting-flight-delays-using-python-and-griddb","status":"publish","type":"post","link":"https:\/\/griddb.net\/en\/blog\/predicting-flight-delays-using-python-and-griddb\/","title":{"rendered":"Predicting flight delays using Python and GridDB"},"content":{"rendered":"
\n
\n
\n
\n
\n<\/div>\n
\n<\/div>
\n

Due to the associated financial losses that the aviation industry is constantly experiencing, flight delays have become a very important topic for air transportation all over the world.<\/p>\n

The causes of these delays are many and diverse, ranging from air traffic congestion to weather conditions, mechanical issues, challenges with passenger boarding, and simply the airlines' inability to meet demand given their capacity.<\/p>\n

Based on historical data of flight delays, we will first analyse the reasons for delays and then we will predict flight delay time prediction.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n

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

The outline of the tutorial is as follows:<\/p>\n

    \n
  1. Dataset overview<\/li>\n
  2. Importing required libraries<\/li>\n
  3. Loading the dataset<\/li>\n
  4. Data Preporcessing and data visualization<\/li>\n
  5. Predictions<\/li>\n
  6. Conclusion<\/li>\n<\/ol>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
    \n
    \n
    \n<\/div>\n
    \n<\/div>
    \n

    Prerequisites and Environment setup\u00b6<\/a><\/h1>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
    \n
    \n
    \n<\/div>\n
    \n<\/div>
    \n

    This tutorial is carried out in Anaconda Navigator (Python version \u2013 3.8.5) on Windows Operating System. The following packages need to be installed before you continue with the tutorial \u2013<\/p>\n

      \n

    1. Pandas<\/p>\n<\/li>\n

    2. NumPy<\/p>\n<\/li>\n

    3. sklearn<\/p>\n<\/li>\n

    4. Matplotlib<\/p>\n<\/li>\n

    5. Seaborn<\/p>\n<\/li>\n

    6. statsmodels<\/p>\n<\/li>\n<\/ol>\n

      You can install these packages in Conda\u2019s virtual environment using conda install package-name<\/code>. In case you are using Python directly via terminal\/command prompt, pip install package-name<\/code> will do the work.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n

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

      GridDB installation\u00b6<\/a><\/h3>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
      \n
      \n
      \n<\/div>\n
      \n<\/div>
      \n

      While loading the dataset, this tutorial will cover two methods \u2013 Using GridDB as well as Using Pandas. To access GridDB using Python, the following packages also need to be installed beforehand:<\/p>\n

        \n
      1. GridDB C-client<\/a><\/li>\n
      2. SWIG (Simplified Wrapper and Interface Generator)<\/li>\n
      3. GridDB Python Client<\/a><\/li>\n<\/ol>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
        \n
        \n
        \n<\/div>\n
        \n<\/div>
        \n

        1. Dataset Overview\u00b6<\/a><\/h1>

        The Bureau of Transportation Statistics of the United States Department of Transportation (DOT) monitors the on-time performance of domestic flight operated by large air carriers. The DOT's monthly Air Travel Consumer Report and this dataset of 2015 flight delays and cancellations contain summary information on the number of on-time, delayed, cancelled, and diverted flight.<\/p>\n

        https:\/\/www.kaggle.com\/code\/manasichhibber\/flight-delay-predictions\/data<\/a><\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n

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

        2. Importing Required Libraries\u00b6<\/a><\/h1>\n<\/div>\n<\/div>\n<\/div>\n<\/div>
        \n
        \n
        \n<\/div>\n
        \n
        In\u00a0[1]:<\/div>\n
        \n
        \n
        <\/span>import<\/span> <\/span>pandas<\/span> <\/span>as<\/span> <\/span>pd<\/span>\nimport<\/span> <\/span>seaborn<\/span> <\/span>as<\/span> <\/span>sns<\/span>\nfrom<\/span> <\/span>sklearn.model_selection<\/span> <\/span>import<\/span> train_test_split<\/span>\nfrom<\/span> <\/span>sklearn.preprocessing<\/span> <\/span>import<\/span> StandardScaler<\/span>\nfrom<\/span> <\/span>sklearn.tree<\/span> <\/span>import<\/span> DecisionTreeClassifier<\/span>\nfrom<\/span> <\/span>sklearn.metrics<\/span> <\/span>import<\/span> roc_auc_score<\/span>\nimport<\/span> <\/span>requests<\/span>\nimport<\/span> <\/span>http<\/span>\nhttp<\/span>.<\/span>client<\/span>.<\/span>HTTPConnection<\/span>.<\/span>debuglevel<\/span> =<\/span> 1<\/span>\nfrom<\/span> <\/span>requests.auth<\/span> <\/span>import<\/span> HTTPBasicAuth<\/span>\n\nimport<\/span> <\/span>numpy<\/span> <\/span>as<\/span> <\/span>np<\/span>   \nimport<\/span> <\/span>statsmodels.formula.api<\/span> <\/span>as<\/span> <\/span>sm<\/span>\nimport<\/span> <\/span>datetime<\/span>\nimport<\/span> <\/span>time<\/span>\nfrom<\/span> <\/span>time<\/span> <\/span>import<\/span> strftime<\/span>,<\/span> gmtime<\/span>\nimport<\/span> <\/span>statsmodels.formula.api<\/span> <\/span>as<\/span> <\/span>smf<\/span>\nfrom<\/span> <\/span>sklearn.feature_selection<\/span> <\/span>import<\/span> SelectFromModel<\/span>\nfrom<\/span> <\/span>sklearn.ensemble<\/span> <\/span>import<\/span> RandomForestRegressor<\/span>\nfrom<\/span> <\/span>sklearn.model_selection<\/span> <\/span>import<\/span> train_test_split<\/span>\nfrom<\/span> <\/span>sklearn.metrics<\/span> <\/span>import<\/span> confusion_matrix<\/span> \n\nfrom<\/span> <\/span>sklearn<\/span> <\/span>import<\/span> ensemble<\/span>,<\/span>gaussian_process<\/span>,<\/span>linear_model<\/span>,<\/span>naive_bayes<\/span>,<\/span>neighbors<\/span>,<\/span>svm<\/span>,<\/span>tree<\/span>\nfrom<\/span> <\/span>sklearn.model_selection<\/span> <\/span>import<\/span> cross_val_score<\/span>\nfrom<\/span> <\/span>sklearn.metrics<\/span> <\/span>import<\/span> roc_curve<\/span>,<\/span> roc_auc_score<\/span>,<\/span>precision_score<\/span>,<\/span>recall_score<\/span>,<\/span>auc<\/span>\n\nfrom<\/span> <\/span>sklearn.metrics<\/span> <\/span>import<\/span> mean_absolute_error<\/span>\nfrom<\/span> <\/span>sklearn.svm<\/span> <\/span>import<\/span> SVC<\/span>\nfrom<\/span> <\/span>random<\/span> <\/span>import<\/span> sample<\/span>\n\n\nimport<\/span> <\/span>matplotlib.pyplot<\/span> <\/span>as<\/span> <\/span>plt<\/span>\nplt<\/span>.<\/span>style<\/span>.<\/span>use<\/span>(<\/span>'fivethirtyeight'<\/span>)<\/span>\n\nimport<\/span> <\/span>warnings<\/span>\nwarnings<\/span>.<\/span>filterwarnings<\/span>(<\/span>\"ignore\"<\/span>)<\/span>\n<\/pre><\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
        \n
        \n
        \n<\/div>\n
        \n<\/div>
        \n
        3. Loading the Dataset\u00b6<\/a><\/h1>
        Toshiba GridDB\u2122 is a highly scalable NoSQL database best suited for IoT and Big Data. The foundation of GridDB\u2019s principles is based upon offering a versatile data store that is optimized for IoT, provides high scalability, tuned for high performance, and ensures high reliability.<\/p>\n
        To store large amounts of data, a CSV file can be cumbersome. GridDB serves as a perfect alternative as it in open-source and a highly scalable database. GridDB is a scalable, in-memory, No SQL database which makes it easier for you to store large amounts of data. If you are new to GridDB, a tutorial on  reading and writing to GridDB<\/a>  can be useful.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
        \n
        \n
        \n<\/div>\n
        \n<\/div>
        \n
        Setting up a Container in GridDB to store the data\u00b6<\/a><\/h2>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
        \n
        \n
        \n<\/div>\n
        \n<\/div>
        \n
        The aim of this blog post is to showcase the noteworthy features of GridDB, including:<\/p>\n