{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-06-01T12:19:58.498885Z","iopub.execute_input":"2023-06-01T12:19:58.499265Z","iopub.status.idle":"2023-06-01T12:19:58.508955Z","shell.execute_reply.started":"2023-06-01T12:19:58.499236Z","shell.execute_reply":"2023-06-01T12:19:58.507793Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":" **********Your opinions and suggestions are totally welcome","metadata":{}},{"cell_type":"markdown","source":"Let's start with reading data to have an overview about how it looks like","metadata":{}},{"cell_type":"code","source":"df = pd.read_csv('/kaggle/input/2023-kaggle-ai-report/kaggle_writeups_20230510.csv')\n\nsubmission = pd.read_csv('/kaggle/input/2023-kaggle-ai-report/sample_submission.csv')","metadata":{"execution":{"iopub.status.busy":"2023-06-01T12:20:04.725927Z","iopub.execute_input":"2023-06-01T12:20:04.726337Z","iopub.status.idle":"2023-06-01T12:20:05.156660Z","shell.execute_reply.started":"2023-06-01T12:20:04.726302Z","shell.execute_reply":"2023-06-01T12:20:05.155696Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission.head()","metadata":{"execution":{"iopub.status.busy":"2023-06-01T12:20:08.307351Z","iopub.execute_input":"2023-06-01T12:20:08.307864Z","iopub.status.idle":"2023-06-01T12:20:08.340123Z","shell.execute_reply.started":"2023-06-01T12:20:08.307822Z","shell.execute_reply":"2023-06-01T12:20:08.339357Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# EDA","metadata":{}},{"cell_type":"markdown","source":"data wrangling to explore more about our dataset","metadata":{}},{"cell_type":"code","source":"df.head()","metadata":{"execution":{"iopub.status.busy":"2023-05-27T15:47:52.558371Z","iopub.execute_input":"2023-05-27T15:47:52.559163Z","iopub.status.idle":"2023-05-27T15:47:52.592294Z","shell.execute_reply.started":"2023-05-27T15:47:52.559130Z","shell.execute_reply":"2023-05-27T15:47:52.591344Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df.describe()","metadata":{"execution":{"iopub.status.busy":"2023-05-27T15:47:55.293145Z","iopub.execute_input":"2023-05-27T15:47:55.293623Z","iopub.status.idle":"2023-05-27T15:47:55.348347Z","shell.execute_reply.started":"2023-05-27T15:47:55.293585Z","shell.execute_reply":"2023-05-27T15:47:55.347333Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df.info()","metadata":{"execution":{"iopub.status.busy":"2023-05-27T15:36:17.827810Z","iopub.execute_input":"2023-05-27T15:36:17.828793Z","iopub.status.idle":"2023-05-27T15:36:17.856568Z","shell.execute_reply.started":"2023-05-27T15:36:17.828752Z","shell.execute_reply":"2023-05-27T15:36:17.855131Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#checking if there is any null rows\ndf.isnull().sum()","metadata":{"execution":{"iopub.status.busy":"2023-05-27T15:36:46.289774Z","iopub.execute_input":"2023-05-27T15:36:46.290772Z","iopub.status.idle":"2023-05-27T15:36:46.308415Z","shell.execute_reply.started":"2023-05-27T15:36:46.290729Z","shell.execute_reply":"2023-05-27T15:36:46.307223Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Data cleaning","metadata":{}},{"cell_type":"code","source":"#checking if there is any duplicated rows\ndf.duplicated().sum()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#deleting non_availble rows\ndf.dropna(inplace=True)","metadata":{"execution":{"iopub.status.busy":"2023-05-27T15:47:58.202554Z","iopub.execute_input":"2023-05-27T15:47:58.202956Z","iopub.status.idle":"2023-05-27T15:47:58.215559Z","shell.execute_reply.started":"2023-05-27T15:47:58.202922Z","shell.execute_reply":"2023-05-27T15:47:58.214496Z"},"trusted":true},"execution_count":null,"outputs":[]}]}