Close to 24k on dev

.ipynb_checkpoints/Auta-checkpoint.ipynb

@@ -0,0 +1,49 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.linear_model import LinearRegression\n",
+    "from sklearn.metrics import mean_squared_error\n",
+    "import seaborn as sns\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df =pd.read_csv('train/train.csv', sep=\"\\t\")"
+   ]
+  }
+ ],
+ "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
+}

Auta.ipynb

@@ -0,0 +1,218 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 67,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.linear_model import LinearRegression\n",
+    "from sklearn.metrics import mean_squared_error\n",
+    "import seaborn as sns\n",
+    "import matplotlib.pyplot as plt\n",
+    "from sklearn.preprocessing import PolynomialFeatures"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 115,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "col_names = [\"Price\",\"Mileage\",\"Year\",\"Brand\",\"EngineType\",\"EngineCapacity\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 116,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df =pd.read_csv('train/train.tsv', sep=\"\\t\", names=col_names)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 187,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def prepareData(df):\n",
+    "    df[\"Age\"] = 2018 - df[\"Year\"]\n",
+    "    df[\"SqrtAge\"] = df.age**0.5\n",
+    "    df[\"SqrtMileage\"] = df.Mileage ** 0.5\n",
+    "    df[\"SqrtEngineCapacity\"] = df.EngineCapacity ** 0.5\n",
+    "    df = pd.concat([df, df['EngineType'].str.get_dummies()], axis = 1 )\n",
+    "    df = df.drop(['EngineType','Brand'], axis = 1)\n",
+    "    poly = PolynomialFeatures(2, interaction_only=True)\n",
+    "    df = poly.fit_transform(df)\n",
+    "    return df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 188,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_train = df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 190,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_train = df_train.Price\n",
+    "x_train = df_train.drop('Price', axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 191,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x_train = prepareData(x_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 192,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "LinearRegression()"
+      ]
+     },
+     "execution_count": 192,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "linReg = LinearRegression()\n",
+    "linReg.fit(x_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 193,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_dev =pd.read_csv('dev-0/expected.tsv', sep=\"\\t\", names=[\"Price\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 194,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x_dev =pd.read_csv('dev-0/in.tsv', sep=\"\\t\", names=[\"Mileage\",\"Year\",\"Brand\",\"EngineType\",\"EngineCapacity\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 195,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x_dev = prepareData(x_dev)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 196,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.7535351650926749\n"
+     ]
+    }
+   ],
+   "source": [
+    "score = linReg.score(x_dev, y_dev)\n",
+    "print(score)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 197,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = linReg.predict(x_dev)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 198,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = {'Price':y_pred}\n",
+    "y_pred = pd.DataFrame(data)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 199,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "24989.603665517054"
+      ]
+     },
+     "execution_count": 199,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mean_squared_error(y_dev, y_pred, squared=False)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "24943.930732282024\n",
+    "26863.621497665004 #BEZ AGE\n"
+   ]
+  }
+ ],
+ "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
+}

Auta.py

@@ -0,0 +1,59 @@
+import pandas as pd
+from sklearn.linear_model import LinearRegression
+from sklearn.metrics import mean_squared_error
+from sklearn.preprocessing import PolynomialFeatures
+
+col_names = ["Price","Mileage","Year","Brand","EngineType","EngineCapacity"]
+
+
+
+def prepareData(df):
+    df["Age"] = 2018 - df["Year"]
+    df["SqrtAge"] = df.Age**0.5
+    df = pd.concat([df, df['EngineType'].str.get_dummies()], axis = 1 )
+    df = df.drop(['EngineType','Brand'], axis = 1)
+    df["SqrtMileage"] = df.Mileage ** 0.5
+    df["SqrtEngineCapacity"] = df.EngineCapacity ** 0.5
+    poly = PolynomialFeatures(2, interaction_only=True)
+    df = poly.fit_transform(df)
+    return df
+
+def main():
+
+    df =pd.read_csv('train/train.tsv', sep="\t", names=col_names)
+    y_dev =pd.read_csv('dev-0/expected.tsv', sep="\t", names=["Price"])
+    x_dev =pd.read_csv('dev-0/in.tsv', sep="\t", names=["Mileage","Year","Brand","EngineType","EngineCapacity"])
+    x_test =pd.read_csv('test-A/in.tsv', sep="\t", names=["Mileage","Year","Brand","EngineType","EngineCapacity"])
+
+    y_train = df.Price
+    x_train = df.drop('Price', axis=1)
+
+    x_train = prepareData(x_train)
+
+    linReg = LinearRegression()
+    linReg.fit(x_train, y_train)
+
+    x_dev = prepareData(x_dev)
+    x_test = prepareData(x_test)
+
+    #Score modelu dla zbioru dev
+    score = linReg.score(x_dev, y_dev)
+    print(score)
+
+    #Wartość RMSE dla zbioru dev
+    y_pred = linReg.predict(x_dev)
+    data = {'Price':y_pred}
+    y_pred = pd.DataFrame(data)
+    rmse = mean_squared_error(y_dev, y_pred, squared=False)
+    print(rmse)
+
+    #predict dla test-A
+    y_pred_test = linReg.predict(x_test)
+    data = {'Price':y_pred_test}
+    y_pred_test = pd.DataFrame(data)
+
+    y_pred_test.to_csv(r'test-A/out.tsv', sep='\t')
+
+
+if __name__ == "__main__":
+    main()