{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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 in \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 \"../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# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"!pip install plotly","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import plotly.express as px\ndf = pd.read_csv(r\"/kaggle/input/bengaliai-cv19/train.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig = px.histogram(df, x=\"grapheme_root\", histnorm='probability', title=\"Grapheme Occurance Count in order of Grapheme Root\")\nfig.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Grapheme Count: \ndfb = df.groupby(\"grapheme_root\").count()\nfig = px.bar(dfb[\"grapheme\"].sort_values(), y=\"grapheme\", title=\"Grapheme Occurance Count Sorted from Low to High\")\nfig.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#%%\n# Vowel Diacritic Count\nfig = px.histogram(df, x=\"vowel_diacritic\", title=\"Vowel Diacritic Occurance Count\")\nfig.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#%%\ndfb = df.groupby(\"vowel_diacritic\").count()\nfig = px.bar(dfb[\"grapheme\"].sort_values(), y=\"grapheme\", title=\"Vowel Diacritic Occurance Count Sorted from Low to High\")\nfig.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#%%\nfig = px.histogram(df, x=\"consonant_diacritic\", title=\"Vowel Diacritic Occurance Count\")\nfig.show()\n#%%","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Grapheme Count: \ndfb = df.groupby(\"consonant_diacritic\").count()\nfig = px.bar(dfb[\"grapheme\"].sort_values(), y=\"grapheme\", title=\"Consonant Diacritic Occurance Count Sorted from Low to High\")\nfig.show()\n#%%\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":1}