{"id":46662,"date":"2021-09-01T00:00:00","date_gmt":"2021-09-01T07:00:00","guid":{"rendered":"https:\/\/griddb-linux-hte8hndjf8cka8ht.westus-01.azurewebsites.net\/blog\/movie-review-classification-using-nlp-griddb-and-python\/"},"modified":"2025-11-13T12:55:33","modified_gmt":"2025-11-13T20:55:33","slug":"movie-review-classification-using-nlp-griddb-and-python","status":"publish","type":"post","link":"https:\/\/griddb.net\/en\/blog\/movie-review-classification-using-nlp-griddb-and-python\/","title":{"rendered":"Movie Review Classification Using NLP, GridDB, and Python"},"content":{"rendered":"

Introduction<\/h2>\n

In this tutorial, we will be classifying movie reviews based on sentimental analysis using an NLP Model. This is an application-based tutorial where we will be using a pre-trained LSTM model from the Allen NLP library. The outline of the tutorial is as follows:<\/p>\n

    \n
  1. Setting up the environment<\/li>\n
  2. All about the Dataset<\/li>\n
  3. Data Preprocessing<\/li>\n
  4. Loading the Allen NLP model<\/li>\n
  5. Making predictions<\/li>\n
  6. Evaluating the results<\/li>\n<\/ol>\n

    The full Jupyter file can be seen on our GitHub Page<\/a><\/p>\n

    Setting up the environment<\/h2>\n

    This tutorial is carried out in Jupyter Notebooks (Anaconda version 4.8.3) with Python version 3.8 on Windows 10 Operating system. Following packages need to be installed before you continue with the code:<\/p>\n

      \n
    1. Pandas<\/a><\/li>\n
    2. allennlp<\/a><\/li>\n
    3. allennlp-models<\/a><\/li>\n
    4. nltk<\/a><\/li>\n
    5. scikit-learn<\/a><\/li>\n<\/ol>\n

      You can install the above-mentioned packages using pip<\/code> or conda<\/code>. Simply type pip install package-name<\/code> or conda install package-name<\/code> in the command line.<\/p>\n

      To access GridDB’s database through Python<\/a>, the following packages will be required:<\/p>\n

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

        All About the Dataset<\/h2>\n

        We are using the IMDB Sentiment Analysis Dataset which is available publicly on Kaggle<\/a>. The format of the dataset is pretty simple – it has 2 attributes:<\/p>\n

          \n
        1. Movie Review (string)<\/li>\n
        2. Sentiment Label (int) – Binary<\/li>\n<\/ol>\n

          A label ‘0’ represents a negative movie review whereas ‘1’ represents a positive movie review. Since we will be using a pre-trained model, there is no need to download the train and validation dataset. We will be utilizing only the test dataset which has 5000 instances. Once you download the dataset, put it in the same working directory.<\/p>\n

          Now let’s go ahead and load the dataset in our python environment<\/p>\n

          Loading the Data<\/h3>\n

          GridDB has made it easier to work with data as we can directly call the database using its python-client and load it in the form of pandas dataframe.<\/p>\n

          \n
          import griddb_python as griddb\nimport pandas as pd\n\nsql_statement = ('SELECT * FROM movie_review_test')\nmovie_review_test = pd.read_sql_query(sql_statement, cont)<\/code><\/pre>\n<\/div>\n
          The cont<\/code> variable has the container information in which you have your data stored. A detailed tutorial on reading and writing to GridDB using Pandas<\/a> is available on the blog.<\/p>\n
          Alternatively, if you have the CSV file, you can use the read_csv() function of pandas. The outcome will be the same in both scenarios<\/p>\n
          \n
          import pandas as pd\n\nmovie_review_test = pd.read_csv(\"movie_review_test.csv\")<\/code><\/pre>\n<\/div>\n
          Let’s print out the first five rows to get a little sneak peak into our data<\/p>\n
          \n
          movie_review_test.head()<\/code><\/pre>\n<\/div>\n
          \n