output for train[:100000]

svm.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 1,
    "id": "fc8ba0a3",
    "metadata": {},
    "outputs": [],
@@ -29,16 +29,38 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "with open(\"train/in.tsv\") as f:\n",
+    "with open(\"train/in.tsv\", encoding='utf-8') as f:\n",
     "    x_train = f.readlines()\n",
     "\n",
-    "with open(\"train/expected.tsv\") as f:\n",
+    "\n",
+    "with open(\"train/expected.tsv\", encoding='utf-8') as f:\n",
     "    y_train = f.readlines()"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 3,
+   "id": "e7630105",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "289579"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(x_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
    "id": "f6bd3ba5",
    "metadata": {},
    "outputs": [],
@@ -48,28 +70,70 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "id": "eefd7b1b",
    "metadata": {},
    "outputs": [],
    "source": [
-    "with open(\"dev-0/in.tsv\") as f:\n",
-    "    x_dev = f.readlines()"
+    "with open(\"svm/in.tsv\", encoding='utf-8') as f:\n",
+    "    x_dev = f.readlines()\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
+   "id": "effadd92",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x_train = x_train[:100000]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "3981d3cb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_train = y_train[:100000]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "bef853f6",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "100000"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\n",
+    "len(y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
    "id": "6696a4d0",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "array([1, 0, 0, ..., 0, 0, 1])"
+       "array([1, 0, 0, ..., 0, 0, 0], dtype=int64)"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -81,7 +145,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 11,
    "id": "5488f657",
    "metadata": {},
    "outputs": [],
@@ -91,7 +155,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 12,
    "id": "ddbb1608",
    "metadata": {},
    "outputs": [],
@@ -101,7 +165,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 13,
    "id": "b286bec3",
    "metadata": {},
    "outputs": [],
@@ -111,7 +175,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 14,
    "id": "0b1fac69",
    "metadata": {},
    "outputs": [],