{ "cells": [ { "cell_type": "code", "execution_count": 152, "metadata": {}, "outputs": [], "source": [ "path=r\"C:\\Users\\HARDYMA\\Synchro\\tg_TG\\\\\"" ] }, { "cell_type": "code", "execution_count": 153, "metadata": {}, "outputs": [], "source": [ "import pandas as pd" ] }, { "cell_type": "code", "execution_count": 174, "metadata": {}, "outputs": [], "source": [ "df=pd.read_csv(path+\"tg_TG.aff.csv\", sep=\"\\t\")\n", "df.columns=[\"FLAG\", \"num\", \"col3\", \"word\", \"col5\", \"col6\"]\n", "df.drop([\"col3\",\"col5\",\"FLAG\"], axis=1, inplace=True )\n", "df[\"word\"]=df[\"word\"].apply(yo)" ] }, { "cell_type": "code", "execution_count": 175, "metadata": {}, "outputs": [], "source": [ "def yo(l):\n", " return l.replace(\"я\",\"jа\").replace(\"ю\",\"jу\").replace(\"ё\",\"jо\").replace(\"Ю\",\"Jу\").replace(\"Я\",\"Jа\").replace(\"Ё\",\"Jо\")" ] }, { "cell_type": "code", "execution_count": 176, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
numwordcol6
01ад5
11адам6
21адат7
31адатон8
41адаш9
............
3231862иjу4927
3232863иjам4930
3233863иjаму4931
3234863иjаш4932
3235863иjашу4933
\n", "

3236 rows × 3 columns

\n", "
" ], "text/plain": [ " num word col6\n", "0 1 ад 5\n", "1 1 адам 6\n", "2 1 адат 7\n", "3 1 адатон 8\n", "4 1 адаш 9\n", "... ... ... ...\n", "3231 862 иjу 4927\n", "3232 863 иjам 4930\n", "3233 863 иjаму 4931\n", "3234 863 иjаш 4932\n", "3235 863 иjашу 4933\n", "\n", "[3236 rows x 3 columns]" ] }, "execution_count": 176, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df" ] }, { "cell_type": "code", "execution_count": 177, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[7,\n", " 2,\n", " 4,\n", " 2,\n", " 4,\n", " 5,\n", " 5,\n", " 4,\n", " 1,\n", " 2,\n", " 2,\n", " 2,\n", " 4,\n", " 1,\n", " 1,\n", " 7,\n", " 2,\n", " 2,\n", " 2,\n", " 3,\n", " 3,\n", " 3,\n", " 3,\n", " 37,\n", " 14,\n", " 23,\n", " 15,\n", " 24,\n", " 64,\n", " 4,\n", " 25,\n", " 4,\n", " 31,\n", " 21,\n", " 2,\n", " 9,\n", " 3,\n", " 8,\n", " 1,\n", " 1,\n", " 31,\n", " 9,\n", " 7,\n", " 1,\n", " 1,\n", " 1,\n", " 20,\n", " 3,\n", " 5,\n", " 1,\n", " 2,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 4,\n", " 1,\n", " 2,\n", " 1,\n", " 1,\n", " 1,\n", " 15,\n", " 8,\n", " 1,\n", " 1,\n", " 11,\n", " 2,\n", " 6,\n", " 3,\n", " 1,\n", " 1,\n", " 1,\n", " 3,\n", " 1,\n", " 3,\n", " 2,\n", " 2,\n", " 2,\n", " 1,\n", " 13,\n", " 1,\n", " 2,\n", " 3,\n", " 3,\n", " 1,\n", " 4,\n", " 2,\n", " 1,\n", " 1,\n", " 1,\n", " 2,\n", " 17,\n", " 10,\n", " 1,\n", " 16,\n", " 1,\n", " 3,\n", " 1,\n", " 2,\n", " 1,\n", " 3,\n", " 22,\n", " 5,\n", " 2,\n", " 1,\n", " 1,\n", " 11,\n", " 1,\n", " 1,\n", " 14,\n", " 1,\n", " 2,\n", " 3,\n", " 6,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 2,\n", " 3,\n", " 7,\n", " 1,\n", " 1,\n", " 1,\n", " 3,\n", " 1,\n", " 1,\n", " 2,\n", " 1,\n", " 5,\n", " 1,\n", " 3,\n", " 1,\n", " 3,\n", " 1,\n", " 1,\n", " 12,\n", " 4,\n", " 8,\n", " 1,\n", " 1,\n", " 4,\n", " 1,\n", " 9,\n", " 3,\n", " 5,\n", " 2,\n", " 4,\n", " 3,\n", " 2,\n", " 2,\n", " 17,\n", " 8,\n", " 9,\n", " 3,\n", " 1,\n", " 1,\n", " 8,\n", " 2,\n", " 13,\n", " 2,\n", " 9,\n", " 3,\n", " 1,\n", " 1,\n", " 1,\n", " 10,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 8,\n", " 2,\n", " 3,\n", " 5,\n", " 2,\n", " 1,\n", " 3,\n", " 2,\n", " 2,\n", " 14,\n", " 5,\n", " 1,\n", " 9,\n", " 1,\n", " 2,\n", " 1,\n", " 2,\n", " 3,\n", " 18,\n", " 3,\n", " 8,\n", " 4,\n", " 5,\n", " 1,\n", " 2,\n", " 1,\n", " 2,\n", " 1,\n", " 1,\n", " 3,\n", " 7,\n", " 2,\n", " 1,\n", " 1,\n", " 3,\n", " 1,\n", " 1,\n", " 3,\n", " 5,\n", " 4,\n", " 1,\n", " 2,\n", " 6,\n", " 1,\n", " 1,\n", " 2,\n", " 28,\n", " 9,\n", " 1,\n", " 1,\n", " 3,\n", " 1,\n", " 16,\n", " 2,\n", " 11,\n", " 3,\n", " 4,\n", " 2,\n", " 1,\n", " 1,\n", " 13,\n", " 1,\n", " 5,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 11,\n", " 3,\n", " 2,\n", " 3,\n", " 11,\n", " 5,\n", " 1,\n", " 1,\n", " 2,\n", " 1,\n", " 16,\n", " 8,\n", " 2,\n", " 3,\n", " 3,\n", " 1,\n", " 15,\n", " 15,\n", " 5,\n", " 1,\n", " 3,\n", " 2,\n", " 2,\n", " 2,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 18,\n", " 6,\n", " 13,\n", " 1,\n", " 1,\n", " 1,\n", " 3,\n", " 4,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 9,\n", " 2,\n", " 2,\n", " 1,\n", " 2,\n", " 10,\n", " 1,\n", " 5,\n", " 4,\n", " 2,\n", " 1,\n", " 2,\n", " 3,\n", " 2,\n", " 2,\n", " 1,\n", " 17,\n", " 3,\n", " 2,\n", " 3,\n", " 1,\n", " 1,\n", " 3,\n", " 2,\n", " 4,\n", " 1,\n", " 3,\n", " 1,\n", " 2,\n", " 1,\n", " 1,\n", " 8,\n", " 1,\n", " 1,\n", " 1,\n", " 3,\n", " 1,\n", " 6,\n", " 2,\n", " 1,\n", " 1,\n", " 4,\n", " 7,\n", " 1,\n", " 2,\n", " 8,\n", " 1,\n", " 1,\n", " 10,\n", " 5,\n", " 1,\n", " 1,\n", " 3,\n", " 5,\n", " 1,\n", " 20,\n", " 3,\n", " 4,\n", " 1,\n", " 9,\n", " 3,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 5,\n", " 1,\n", " 1,\n", " 1,\n", " 11,\n", " 1,\n", " 2,\n", " 1,\n", " 1,\n", " 1,\n", " 25,\n", " 1,\n", " 5,\n", " 26,\n", " 5,\n", " 2,\n", " 1,\n", " 1,\n", " 10,\n", " 5,\n", " 1,\n", " 1,\n", " 5,\n", " 2,\n", " 3,\n", " 1,\n", " 13,\n", " 4,\n", " 11,\n", " 2,\n", " 3,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 6,\n", " 2,\n", " 1,\n", " 2,\n", " 8,\n", " 1,\n", " 4,\n", " 1,\n", " 5,\n", " 1,\n", " 2,\n", " 5,\n", " 1,\n", " 4,\n", " 3,\n", " 2,\n", " 1,\n", " 1,\n", " 15,\n", " 1,\n", " 7,\n", " 1,\n", " 3,\n", " 10,\n", " 3,\n", " 1,\n", " 2,\n", " 1,\n", " 1,\n", " 1,\n", " 20,\n", " 3,\n", " 1,\n", " 2,\n", " 7,\n", " 14,\n", " 1,\n", " 1,\n", " 3,\n", " 1,\n", " 2,\n", " 1,\n", " 2,\n", " 1,\n", " 1,\n", " 3,\n", " 4,\n", " 1,\n", " 6,\n", " 1,\n", " 3,\n", " 1,\n", " 1,\n", " 3,\n", " 1,\n", " 1,\n", " 4,\n", " 1,\n", " 4,\n", " 1,\n", " 2,\n", " 2,\n", " 11,\n", " 4,\n", " 1,\n", " 10,\n", " 3,\n", " 4,\n", " 1,\n", " 1,\n", " 4,\n", " 1,\n", " 2,\n", " 3,\n", " 1,\n", " 2,\n", " 1,\n", " 1,\n", " 6,\n", " 3,\n", " 1,\n", " 1,\n", " 3,\n", " 17,\n", " 16,\n", " 3,\n", " 8,\n", " 2,\n", " 5,\n", " 3,\n", " 1,\n", " 2,\n", " 8,\n", " 2,\n", " 1,\n", " 3,\n", " 1,\n", " 1,\n", " 5,\n", " 3,\n", " 2,\n", " 1,\n", " 5,\n", " 1,\n", " 1,\n", " 7,\n", " 6,\n", " 2,\n", " 4,\n", " 2,\n", " 1,\n", " 3,\n", " 1,\n", " 2,\n", " 4,\n", " 3,\n", " 1,\n", " 6,\n", " 4,\n", " 2,\n", " 5,\n", " 1,\n", " 1,\n", " 2,\n", " 1,\n", " 2,\n", " 1,\n", " 2,\n", " 5,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 7,\n", " 4,\n", " 1,\n", " 6,\n", " 2,\n", " 1,\n", " 1,\n", " 7,\n", " 3,\n", " 1,\n", " 2,\n", " 4,\n", " 2,\n", " 1,\n", " 1,\n", " 16,\n", " 13,\n", " 3,\n", " 3,\n", " 1,\n", " 2,\n", " 1,\n", " 14,\n", " 4,\n", " 1,\n", " 2,\n", " 3,\n", " 2,\n", " 7,\n", " 1,\n", " 2,\n", " 4,\n", " 2,\n", " 2,\n", " 1,\n", " 3,\n", " 3,\n", " 2,\n", " 1,\n", " 3,\n", " 3,\n", " 3,\n", " 1,\n", " 2,\n", " 10,\n", " 2,\n", " 10,\n", " 3,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 4,\n", " 2,\n", " 1,\n", " 16,\n", " 12,\n", " 3,\n", " 2,\n", " 6,\n", " 3,\n", " 4,\n", " 2,\n", " 4,\n", " 4,\n", " 1,\n", " 1,\n", " 1,\n", " 11,\n", " 1,\n", " 1,\n", " 1,\n", " 3,\n", " 2,\n", " 1,\n", " 2,\n", " 6,\n", " 2,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 7,\n", " 1,\n", " 2,\n", " 5,\n", " 1,\n", " 5,\n", " 3,\n", " 1,\n", " 1,\n", " 4,\n", " 1,\n", " 1,\n", " 4,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 2,\n", " 17,\n", " 2,\n", " 3,\n", " 7,\n", " 2,\n", " 1,\n", " 4,\n", " 3,\n", " 1,\n", " 3,\n", " 2,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 2,\n", " 3,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 12,\n", " 2,\n", " 12,\n", " 1,\n", " 1,\n", " 3,\n", " 10,\n", " 1,\n", " 2,\n", " 5,\n", " 2,\n", " 13,\n", " 3,\n", " 18,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 9,\n", " 2,\n", " 6,\n", " 3,\n", " 3,\n", " 1,\n", " 1,\n", " 2,\n", " 1,\n", " 1,\n", " 2,\n", " 3,\n", " 1,\n", " 2,\n", " 3,\n", " 17,\n", " 6,\n", " 1,\n", " 7,\n", " 2,\n", " 3,\n", " 2,\n", " 5,\n", " 3,\n", " 4,\n", " 1,\n", " 1,\n", " 5,\n", " 1,\n", " 1,\n", " 14,\n", " 5,\n", " 3,\n", " 9,\n", " 3,\n", " 1,\n", " 2,\n", " 1,\n", " 3,\n", " 1,\n", " 2,\n", " 3,\n", " 1,\n", " 1,\n", " 1,\n", " 2,\n", " 1,\n", " 3,\n", " 1,\n", " 3,\n", " 1,\n", " 6,\n", " 3,\n", " 7,\n", " 1,\n", " 1,\n", " 1,\n", " 13,\n", " 1,\n", " 1,\n", " 8,\n", " 2,\n", " 2,\n", " 9,\n", " 6,\n", " 2,\n", " 1,\n", " 2,\n", " 1,\n", " 1,\n", " 4,\n", " 3,\n", " 1,\n", " 14,\n", " 3,\n", " 5,\n", " 10,\n", " 1,\n", " 4,\n", " 1,\n", " 1,\n", " 2,\n", " 3,\n", " 11,\n", " 5,\n", " 1,\n", " 3,\n", " 3,\n", " 17,\n", " 4,\n", " 5,\n", " 2,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 12,\n", " 6,\n", " 1,\n", " 5,\n", " 3,\n", " 2,\n", " 1,\n", " 1,\n", " 1,\n", " 4,\n", " 1,\n", " 7,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 1,\n", " 8,\n", " 18,\n", " 1,\n", " 14,\n", " 2,\n", " 1,\n", " 1,\n", " 2,\n", " 1,\n", " 2,\n", " 3,\n", " 1,\n", " 4,\n", " 1,\n", " 1,\n", " 1,\n", " 3,\n", " 1,\n", " 1,\n", " 1,\n", " 3,\n", " 1,\n", " 2,\n", " 1,\n", " 4,\n", " 7,\n", " 1,\n", " 6,\n", " 1,\n", " 1,\n", " 1,\n", " 13,\n", " 3,\n", " 1,\n", " 1,\n", " 3,\n", " 12,\n", " 3,\n", " 4,\n", " 1,\n", " 1,\n", " 3,\n", " 1,\n", " 1,\n", " 1,\n", " 17,\n", " 3,\n", " 7,\n", " 2,\n", " 8,\n", " 1,\n", " 2,\n", " 1,\n", " 4,\n", " 1,\n", " 1,\n", " 8,\n", " 5,\n", " 3,\n", " 4,\n", " 2,\n", " 2,\n", " 4,\n", " 1,\n", " 2,\n", " 1,\n", " 33,\n", " 1,\n", " 2,\n", " 1,\n", " 2,\n", " 1,\n", " 5,\n", " 2,\n", " 7,\n", " 4]" ] }, "execution_count": 177, "metadata": {}, "output_type": "execute_result" } ], "source": [ "list(df.groupby(\"num\").count()[\"word\"])" ] }, { "cell_type": "code", "execution_count": 178, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
list
num
1[ад, адам, адат, адатон, адаш, адашон, аду]
2[ам, аму]
3[амон, амонанд, амонро, амону]
4[анд, анду]
5[ат, атро, атрову, ату]
......
859[и]
860[стам, станд, стед, стем, сти]
861[jамро, jамрову]
862[иам, иаму, иаш, иашон, иашону, иашу, иjу]
863[иjам, иjаму, иjаш, иjашу]
\n", "

848 rows × 1 columns

\n", "
" ], "text/plain": [ " list\n", "num \n", "1 [ад, адам, адат, адатон, адаш, адашон, аду]\n", "2 [ам, аму]\n", "3 [амон, амонанд, амонро, амону]\n", "4 [анд, анду]\n", "5 [ат, атро, атрову, ату]\n", ".. ...\n", "859 [и]\n", "860 [стам, станд, стед, стем, сти]\n", "861 [jамро, jамрову]\n", "862 [иам, иаму, иаш, иашон, иашону, иашу, иjу]\n", "863 [иjам, иjаму, иjаш, иjашу]\n", "\n", "[848 rows x 1 columns]" ] }, "execution_count": 178, "metadata": {}, "output_type": "execute_result" } ], "source": [ "aggsuff=pd.DataFrame({\"list\":df.groupby([\"num\"])[\"word\"].apply(list)})\n", "aggsuff" ] }, { "cell_type": "code", "execution_count": 179, "metadata": {}, "outputs": [], "source": [ "def base(l):\n", " if l[0][-1]==\"ӣ\":\n", " return l[0]\n", " num=min([len(elem) for elem in l])\n", " while len(set([elem[:num] for elem in l]))>1:\n", " num-=1\n", " return l[0][:num]\n", " " ] }, { "cell_type": "code", "execution_count": 180, "metadata": {}, "outputs": [], "source": [ "aggsuff[\"base\"]=aggsuff[\"list\"].apply(lambda x: base(x))" ] }, { "cell_type": "code", "execution_count": 181, "metadata": {}, "outputs": [], "source": [ "def substract(l):\n", " if base(l)[-1]==\"ӣ\":\n", " var_bas=base(l)[:-1]+\"и\"\n", " return [\"+—\"]+[elem.replace(var_bas, \"+\", 1) for elem in l[1:]]\n", " \n", " return [elem.replace(base(l), \"+\", 1) for elem in l]" ] }, { "cell_type": "code", "execution_count": 185, "metadata": { "scrolled": true }, "outputs": [], "source": [ "aggsuff[\"substract\"]=aggsuff[\"list\"].apply(substract)" ] }, { "cell_type": "code", "execution_count": 186, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
listbasesubstract
num
1[ад, адам, адат, адатон, адаш, адашон, аду]ад[+, +ам, +ат, +атон, +аш, +ашон, +у]
2[ам, аму]ам[+, +у]
3[амон, амонанд, амонро, амону]амон[+, +анд, +ро, +у]
4[анд, анду]анд[+, +у]
5[ат, атро, атрову, ату]ат[+, +ро, +рову, +у]
............
859[и]и[+]
860[стам, станд, стед, стем, сти]ст[+ам, +анд, +ед, +ем, +и]
861[jамро, jамрову]jамро[+, +ву]
862[иам, иаму, иаш, иашон, иашону, иашу, иjу]и[+ам, +аму, +аш, +ашон, +ашону, +ашу, +jу]
863[иjам, иjаму, иjаш, иjашу]иjа[+м, +му, +ш, +шу]
\n", "

848 rows × 3 columns

\n", "
" ], "text/plain": [ " list base \\\n", "num \n", "1 [ад, адам, адат, адатон, адаш, адашон, аду] ад \n", "2 [ам, аму] ам \n", "3 [амон, амонанд, амонро, амону] амон \n", "4 [анд, анду] анд \n", "5 [ат, атро, атрову, ату] ат \n", ".. ... ... \n", "859 [и] и \n", "860 [стам, станд, стед, стем, сти] ст \n", "861 [jамро, jамрову] jамро \n", "862 [иам, иаму, иаш, иашон, иашону, иашу, иjу] и \n", "863 [иjам, иjаму, иjаш, иjашу] иjа \n", "\n", " substract \n", "num \n", "1 [+, +ам, +ат, +атон, +аш, +ашон, +у] \n", "2 [+, +у] \n", "3 [+, +анд, +ро, +у] \n", "4 [+, +у] \n", "5 [+, +ро, +рову, +у] \n", ".. ... \n", "859 [+] \n", "860 [+ам, +анд, +ед, +ем, +и] \n", "861 [+, +ву] \n", "862 [+ам, +аму, +аш, +ашон, +ашону, +ашу, +jу] \n", "863 [+м, +му, +ш, +шу] \n", "\n", "[848 rows x 3 columns]" ] }, "execution_count": 186, "metadata": {}, "output_type": "execute_result" } ], "source": [ "aggsuff" ] }, { "cell_type": "code", "execution_count": 187, "metadata": {}, "outputs": [], "source": [ "aggsuff.to_csv(path+\"tg_TG.aff-decomposed.csv\",sep=\"\\t\")" ] }, { "cell_type": "code", "execution_count": 188, "metadata": {}, "outputs": [], "source": [ "from collections import Counter" ] }, { "cell_type": "code", "execution_count": 189, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
substract
+710
+и337
+ро319
+аш134
+у127
......
+овҳо1
+ова1
+оваро1
+ович1
+му1
\n", "

137 rows × 1 columns

\n", "
" ], "text/plain": [ " substract\n", "+ 710\n", "+и 337\n", "+ро 319\n", "+аш 134\n", "+у 127\n", "... ...\n", "+овҳо 1\n", "+ова 1\n", "+оваро 1\n", "+ович 1\n", "+му 1\n", "\n", "[137 rows x 1 columns]" ] }, "execution_count": 189, "metadata": {}, "output_type": "execute_result" } ], "source": [ "suff_freq=pd.DataFrame(Counter(aggsuff[\"substract\"].sum()).values(), index=Counter(aggsuff[\"substract\"].sum()).keys(),columns=[\"substract\"]).sort_values(by=\"substract\",ascending=False)\n", "suff_freq" ] }, { "cell_type": "code", "execution_count": 190, "metadata": {}, "outputs": [], "source": [ "suff_freq.to_csv(path+\"suff_freq.csv\",sep=\"\\t\")" ] }, { "cell_type": "code", "execution_count": 191, "metadata": {}, "outputs": [], "source": [ "import matplotlib.pyplot as plt" ] }, { "cell_type": "code", "execution_count": 192, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
listbasesubstract
num
\n", "
" ], "text/plain": [ "Empty DataFrame\n", "Columns: [list, base, substract]\n", "Index: []" ] }, "execution_count": 192, "metadata": {}, "output_type": "execute_result" } ], "source": [ "aggsuff[aggsuff[\"substract\"].apply(lambda x: len([elem for elem in x if elem[0]!=\"+\"])).apply(lambda x: False if x==0 else True)]" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.4" } }, "nbformat": 4, "nbformat_minor": 2 }