Zaktualizuj 'run.py'

run.py

@@ -1,167 +1,41 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "greenhouse-technician",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "import sklearn\n",
-    "import pandas as pd\n",
-    "from gzip import open as open_gz\n",
-    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
-    "from sklearn.pipeline import make_pipeline\n",
-    "from sklearn.linear_model import LinearRegression\n",
-    "from sklearn.metrics import mean_squared_error"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "acoustic-dividend",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def predict_year(x, path_out, model):\n",
-    "    results = model.predict(x)\n",
-    "    with open(path_out, 'wt') as file:\n",
-    "        for r in results:\n",
-    "            file.write(str(r) + '\\n')       "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "senior-harassment",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "with open('train/train.tsv', 'r', encoding='utf8') as file:\n",
-    "    train = pd.read_csv(file, sep='\\t', names=['Date1', 'Date2', 'Title', 'Author', 'Text'])\n",
-    "    \n",
-    "#train = train[0:10000]\n",
-    "train_x = train['Text']\n",
-    "train['Date'] = (train['Date1'].astype(float) + train['Date2'].astype(float))/2\n",
-    "train_y=train['Date1']"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "polyphonic-coach",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "Pipeline(steps=[('tfidfvectorizer', TfidfVectorizer()),\n",
-       "                ('linearregression', LinearRegression())])"
-      ]
-     },
-     "execution_count": 13,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "model = make_pipeline(TfidfVectorizer(), LinearRegression())\n",
-    "model.fit(train_x, train_y)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "varying-wright",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "with open('dev-0/in.tsv', 'r', encoding='utf8') as file:\n",
-    "    x_dev0 = pd.read_csv(file, header=None, sep='\\t')\n",
-    "x_dev0 = x_dev0[0]  \n",
-    "x_dev0[19999] = 'nie jest'\n",
-    "x_dev0[20000] = 'nie wiem'"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "frozen-ticket",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "with open('dev-1/in.tsv', 'r', encoding='utf8') as file:\n",
-    "    x_dev1 = pd.read_csv(file, header=None, sep='\\t')\n",
-    "x_dev1 = x_dev1[0] "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "8e3a18db-f966-45e4-b881-4b336f188055",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "with open('test-A/in.tsv', 'r', encoding='utf8') as file:\n",
-    "    x_test = pd.read_csv(file, header=None, sep='\\t')\n",
-    "x_test = x_test[0] "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "traditional-amount",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#y_dev = pd.read_csv('dev-0/out.tsv',header = None, sep = '/t',engine = 'python')\n",
-    "#y_dev = y_dev[0]\n",
-    "#y_dev_exp = pd.read_csv('dev-0/expected.tsv',header = None, sep = '/t',engine = 'python')\n",
-    "#y_dev_exp = y_dev_exp[0]\n",
-    "#RMSE_dev = mean_squared_error(y_dev_exp, y_dev) "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "close-clinton",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "predict_year(x_dev0, 'dev-0/out.tsv', model)\n",
-    "predict_year(x_dev1,'dev-1/out.tsv', model)\n",
-    "predict_year(x_test,'test-A/out.tsv', model)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "official-sweet",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "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": "3.9.12"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}
+import os
+import sklearn
+import pandas as pd
+from gzip import open as open_gz
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.pipeline import make_pipeline
+from sklearn.linear_model import LinearRegression
+from sklearn.metrics import mean_squared_error
+
+def predict_year(x, path_out, model):
+    results = model.predict(x)
+    with open(path_out, 'wt') as file:
+        for r in results:
+            file.write(str(r) + '\n')       
+
+def read_file(filename):
+    result = []
+    with open(filename, 'r', encoding="utf-8") as file:
+        for line in file:
+            text = line.split("\t")[0].strip()
+            result.append(text)
+    return result
+
+with open('train/train.tsv', 'r', encoding='utf8') as file:
+    train = pd.read_csv(file, sep='\t', names=['Start', 'End', 'Title', 'Author', 'Text'])
+    
+train = train[0:12000]
+train_x = train['Text']
+#train['Date'] = (train['Start'].astype(float) + train['End'].astype(float))/2
+train_y = train['Start']
+
+model = make_pipeline(TfidfVectorizer(), LinearRegression())
+model.fit(train_x, train_y)
+
+x_dev_0 = read_file('dev-0/in.tsv')
+predict_year(x_dev_0, 'dev-0/out.tsv', model)
+x_dev_1 = read_file('dev-1/in.tsv')
+predict_year(x_dev_1,'dev-1/out.tsv', model)
+x_test = read_file('test-A/in.tsv')
+predict_year(x_test,'test-A/out.tsv', model)
+