zadanie

.ipynb_checkpoints/Untitled-checkpoint.ipynb

@@ -0,0 +1,6 @@
+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

.ipynb_checkpoints/solution-checkpoint.ipynb

@@ -0,0 +1,251 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from pathlib import Path\n",
+    "import seaborn as sns\n",
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "from sklearn.linear_model import LinearRegression"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## TRENING"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "NAMES = [\"Price\",\"Mileage\",\"Year\",\"Brand\",\"EngineType\",\"EngineCapacity\"]\n",
+    "TRAIN_BASE = pd.read_csv(\"train/train.tsv\", sep ='\\t', names=NAMES)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "Y_TRAIN = np.array(TRAIN_BASE[\"Price\"])\n",
+    "X_TRAIN = np.array(TRAIN_BASE[[\"Mileage\",\"Year\",\"EngineCapacity\"]])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "MODEL = LinearRegression().fit(X_TRAIN,Y_TRAIN)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## DEV-0"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "NAMES = [\"Mileage\",\"Year\",\"Brand\",\"EngineType\",\"EngineCapacity\"]\n",
+    "FILE_BASE = pd.read_csv(\"dev-0/in.tsv\", sep ='\\t', names=NAMES)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_TEST = np.array(FILE_BASE[[\"Mileage\",\"Year\",\"EngineCapacity\"]])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "Y_TEST = MODEL.predict(X_TEST)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "VALUES = np.array2string(Y_TEST, precision=5, separator='\\n',suppress_small=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "VALUES = VALUES.split(\".\\n\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "OUTFILE = open(\"dev-0/out.tsv\", \"w\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [],
+   "source": [
+    "for x in VALUES:\n",
+    "    RESULT = x.replace(\" \",\"\")\n",
+    "    RESULT = RESULT.replace(\"[\",\"\")\n",
+    "    RESULT = RESULT.replace(\"]\",\"\")\n",
+    "    OUTFILE.write(str(RESULT)+\"\\n\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "OUTFILE.close()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## TEST A"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "NAMES = [\"Mileage\",\"Year\",\"Brand\",\"EngineType\",\"EngineCapacity\"]\n",
+    "FILE_BASE = pd.read_csv(\"test-A/in.tsv\", sep ='\\t', names=NAMES)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_TEST = np.array(FILE_BASE[[\"Mileage\",\"Year\",\"EngineCapacity\"]])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "Y_TEST = MODEL.predict(X_TEST)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "VALUES = np.array2string(Y_TEST, precision=5, separator='\\n',suppress_small=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "VALUES = VALUES.split(\".\\n\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "OUTFILE = open(\"test-A/out.tsv\", \"w\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for x in VALUES:\n",
+    "    RESULT = x.replace(\" \",\"\").replace(\"[\",\"\").replace(\"]\",\"\")\n",
+    "    OUTFILE.write(str(RESULT) )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "OUTFILE.close()"
+   ]
+  },
+  {
+   "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": "3.8.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

solution.ipynb

@@ -0,0 +1,253 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from pathlib import Path\n",
+    "import seaborn as sns\n",
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "from sklearn.linear_model import LinearRegression"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## TRENING"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "NAMES = [\"Price\",\"Mileage\",\"Year\",\"Brand\",\"EngineType\",\"EngineCapacity\"]\n",
+    "TRAIN_BASE = pd.read_csv(\"train/train.tsv\", sep ='\\t', names=NAMES)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "Y_TRAIN = np.array(TRAIN_BASE[\"Price\"])\n",
+    "X_TRAIN = np.array(TRAIN_BASE[[\"Mileage\",\"Year\",\"EngineCapacity\"]])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "MODEL = LinearRegression().fit(X_TRAIN,Y_TRAIN)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## DEV-0"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "NAMES = [\"Mileage\",\"Year\",\"Brand\",\"EngineType\",\"EngineCapacity\"]\n",
+    "FILE_BASE = pd.read_csv(\"dev-0/in.tsv\", sep ='\\t', names=NAMES)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_TEST = np.array(FILE_BASE[[\"Mileage\",\"Year\",\"EngineCapacity\"]])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "Y_TEST = MODEL.predict(X_TEST)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "VALUES = np.array2string(Y_TEST, precision=5, separator='\\n',suppress_small=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "VALUES = VALUES.split(\".\\n\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "OUTFILE = open(\"dev-0/out.tsv\", \"w\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [],
+   "source": [
+    "for x in VALUES:\n",
+    "    RESULT = x.replace(\" \",\"\")\n",
+    "    RESULT = RESULT.replace(\"[\",\"\")\n",
+    "    RESULT = RESULT.replace(\"]\",\"\")\n",
+    "    OUTFILE.write(str(RESULT))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "OUTFILE.close()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## TEST A"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "NAMES = [\"Mileage\",\"Year\",\"Brand\",\"EngineType\",\"EngineCapacity\"]\n",
+    "FILE_BASE = pd.read_csv(\"test-A/in.tsv\", sep ='\\t', names=NAMES)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_TEST = np.array(FILE_BASE[[\"Mileage\",\"Year\",\"EngineCapacity\"]])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "Y_TEST = MODEL.predict(X_TEST)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "VALUES = np.array2string(Y_TEST, precision=5, separator='\\n',suppress_small=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "VALUES = VALUES.split(\".\\n\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "OUTFILE = open(\"test-A/out.tsv\", \"w\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for x in VALUES:\n",
+    "    RESULT = x.replace(\" \",\"\")\n",
+    "    RESULT = RESULT.replace(\"[\",\"\")\n",
+    "    RESULT = RESULT.replace(\"]\",\"\")\n",
+    "    OUTFILE.write(str(RESULT) )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "OUTFILE.close()"
+   ]
+  },
+  {
+   "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": "3.8.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

solution.py

@@ -0,0 +1,152 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# In[1]:
+
+
+import pandas as pd
+import numpy as np
+from pathlib import Path
+import seaborn as sns
+import matplotlib.pyplot as plt
+import numpy as np
+from sklearn.linear_model import LinearRegression
+
+
+# ## TRENING
+
+# In[2]:
+
+
+NAMES = ["Price","Mileage","Year","Brand","EngineType","EngineCapacity"]
+TRAIN_BASE = pd.read_csv("train/train.tsv", sep ='\t', names=NAMES)
+
+
+# In[3]:
+
+
+Y_TRAIN = np.array(TRAIN_BASE["Price"])
+X_TRAIN = np.array(TRAIN_BASE[["Mileage","Year","EngineCapacity"]])
+
+
+# In[4]:
+
+
+MODEL = LinearRegression().fit(X_TRAIN,Y_TRAIN)
+
+
+# ## DEV-0
+
+# In[5]:
+
+
+NAMES = ["Mileage","Year","Brand","EngineType","EngineCapacity"]
+FILE_BASE = pd.read_csv("dev-0/in.tsv", sep ='\t', names=NAMES)
+
+
+# In[6]:
+
+
+X_TEST = np.array(FILE_BASE[["Mileage","Year","EngineCapacity"]])
+
+
+# In[7]:
+
+
+Y_TEST = MODEL.predict(X_TEST)
+
+
+# In[8]:
+
+
+VALUES = np.array2string(Y_TEST, precision=5, separator='\n',suppress_small=True)
+
+
+# In[9]:
+
+
+VALUES = VALUES.split(".\n")
+
+
+# In[10]:
+
+
+OUTFILE = open("dev-0/out.tsv", "w")
+
+
+# In[11]:
+
+
+for x in VALUES:
+    RESULT = x.replace(" ","")
+    RESULT = RESULT.replace("[","")
+    RESULT = RESULT.replace("]","")
+    OUTFILE.write(str(RESULT))
+
+
+# In[12]:
+
+
+OUTFILE.close()
+
+
+# ## TEST A
+
+# In[13]:
+
+
+NAMES = ["Mileage","Year","Brand","EngineType","EngineCapacity"]
+FILE_BASE = pd.read_csv("test-A/in.tsv", sep ='\t', names=NAMES)
+
+
+# In[14]:
+
+
+X_TEST = np.array(FILE_BASE[["Mileage","Year","EngineCapacity"]])
+
+
+# In[15]:
+
+
+Y_TEST = MODEL.predict(X_TEST)
+
+
+# In[16]:
+
+
+VALUES = np.array2string(Y_TEST, precision=5, separator='\n',suppress_small=True)
+
+
+# In[17]:
+
+
+VALUES = VALUES.split(".\n")
+
+
+# In[18]:
+
+
+OUTFILE = open("test-A/out.tsv", "w")
+
+
+# In[19]:
+
+
+for x in VALUES:
+    RESULT = x.replace(" ","")
+    RESULT = RESULT.replace("[","")
+    RESULT = RESULT.replace("]","")
+    OUTFILE.write(str(RESULT) )
+
+
+# In[20]:
+
+
+OUTFILE.close()
+
+
+# In[ ]:
+
+
+
+