challenging-america-word-ga.../Untitled2.ipynb

1 line
20 KiB
Plaintext
Raw Normal View History

2023-05-10 00:37:23 +02:00
{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"authorship_tag":"ABX9TyPUeZ2ElxrPPHuoVaA9ngsH"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"}},"cells":[{"cell_type":"code","source":[],"metadata":{"id":"dmkDbw6WXAbh","executionInfo":{"status":"ok","timestamp":1682174130713,"user_tz":-120,"elapsed":3,"user":{"displayName":"Martyna Drumińska","userId":"13361003509289187965"}}},"execution_count":null,"outputs":[]},{"cell_type":"code","execution_count":1,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"pFXwuw2YtOWN","executionInfo":{"status":"ok","timestamp":1682174134814,"user_tz":-120,"elapsed":3694,"user":{"displayName":"Martyna Drumińska","userId":"13361003509289187965"}},"outputId":"289968e5-74bb-4bf6-b130-5d19a79d690b"},"outputs":[{"output_type":"stream","name":"stdout","text":["Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"]}],"source":["from google.colab import drive\n","drive.mount('/content/drive')"]},{"cell_type":"code","source":["cd drive/MyDrive"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"blzID9U2XEjl","executionInfo":{"status":"ok","timestamp":1682174134815,"user_tz":-120,"elapsed":14,"user":{"displayName":"Martyna Drumińska","userId":"13361003509289187965"}},"outputId":"a4dbf5ee-ab36-477a-fd52-f93cd91eac73"},"execution_count":2,"outputs":[{"output_type":"stream","name":"stdout","text":["/content/drive/MyDrive\n"]}]},{"cell_type":"code","source":["cd challenging-america-word-gap-prediction/"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"UIvi4ktPXJbr","executionInfo":{"status":"ok","timestamp":1682174134816,"user_tz":-120,"elapsed":13,"user":{"displayName":"Martyna Drumińska","userId":"13361003509289187965"}},"outputId":"9781982b-a123-4ca5-d367-6aac4bdccf1f"},"execution_count":3,"outputs":[{"output_type":"stream","name":"stdout","text":["/content/drive/MyDrive/challenging-america-word-gap-prediction\n"]}]},{"cell_type":"code","source":["import pandas as pd\n","import itertools\n","import collections"],"metadata":{"id":"JBDE5RdCXLoR","executionInfo":{"status":"ok","timestamp":1682174135212,"user_tz":-120,"elapsed":406,"user":{"displayName":"Martyna Drumińska","userId":"13361003509289187965"}}},"execution_count":4,"outputs":[]},{"cell_type":"code","execution_count":20,"metadata":{"id":"pqThz9AaW-0b","executionInfo":{"status":"ok","timestamp":1682174746505,"user_tz":-120,"elapsed":17750,"user":{"displayName":"Martyna Drumińska","userId":"13361003509289187965"}}},"outputs":[],"source":["lists = pd.read_csv(\"list.csv\", sep=\",\", on_bad_lines='skip', encoding=\"utf-8\")"]},{"cell_type":"code","source":["lists"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":423},"id":"jXsHmSmBaBIp","executionInfo":{"status":"ok","timestamp":1682174399937,"user_tz":-120,"elapsed":6,"user":{"displayName":"Martyna Drumińska","userId":"13361003509289187965"}},"outputId":"b3aa5134-618e-411f-d00d-ff1dbd6a55e5"},"execution_count":8,"outputs":[{"output_type":"execute_result","data":{"text/plain":[" col1\n","0 came\n","1 fiom\n","2 the\n","3 last\n","4 place\n","... ...\n","76790221 some\n","76790222 immigrant\n","76790223 hand\n","76790224 before\n","76790225 beingnvertaken\n","\n","[76790226 rows x 1 columns]"],"text/html":["\n"," <div id=\"df-03867be1-4aab-4698-9d14-bd3f1e20a154\">\n"," <div class=\"colab-df-container\">\n"," <div>\n","<style scoped>\n"," .dataframe tbody tr th:only-of-type {\n"," vertical-align: middle;\n"," }\n","\n"," .dataframe tbody tr th {\n"," vertical-align: top;\n"," }\n","\n"," .dataframe thead th {\n"," text-align: right;\n"," }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n"," <thead>\n"," <tr style=\"text-align: right;\">\n"," <th></th>\n","