Add project solution

This commit is contained in:
s430705 2021-06-15 12:56:28 +02:00
commit 953cf03b68
5 changed files with 51034 additions and 0 deletions

1000
dev-0/expected.tsv Normal file

File diff suppressed because it is too large Load Diff

1000
dev-0/in.tsv Normal file

File diff suppressed because it is too large Load Diff

855
regression.ipynb Normal file
View File

@ -0,0 +1,855 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"from pandas import DataFrame\n",
"from sklearn import preprocessing\n",
"from sklearn.preprocessing import PolynomialFeatures\n",
"from sklearn.linear_model import LinearRegression\n",
"from sklearn.metrics import mean_squared_error\n",
"from sklearn import ensemble\n",
"from tensorflow.keras.layers import Input, Dense\n",
"from tensorflow.keras.models import Model"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Cel projektu\n",
"\n",
"Celem projektu jest stworzenie różnych modeli, których zadanie polega na predykcji\n",
"cen poszczególnych samochodów na podstawie danych takich jak:\n",
" - rok produkcji\n",
" - przebieg\n",
" - marka\n",
" - rodzaj silnika\n",
" - pojemność silnika\n",
" "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Wczytywanie danych\n",
"\n",
"Zbiór zawiera listę samochodów, wraz z ich najważniejszymi cechami.\n",
"Rozmiar zbioru: 47930 wierszy × 5 kolumn"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [],
"source": [
"col_names = [\"price\", \"mileage\", \"year\", \"brand\", \"engine_type\", \"engine_cap\"]\n",
"col_names_in = [\"mileage\", \"year\", \"brand\", \"engine_type\", \"engine_cap\"]\n",
"df_train = pd.read_csv(\n",
" \"train/train.tsv\", error_bad_lines=False, header=None, sep=\"\\t\", names=col_names\n",
")\n",
"df = df_train\n",
"test = pd.read_csv(\n",
" \"dev-0/in.tsv\", error_bad_lines=False, header=None, sep=\"\\t\", names=col_names_in\n",
")\n",
"\n",
"\n",
"test_expected = pd.read_csv(\"dev-0/expected.tsv\", error_bad_lines=False, header=None, sep=\"\\t\")"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>mileage</th>\n",
" <th>year</th>\n",
" <th>brand</th>\n",
" <th>engine_type</th>\n",
" <th>engine_cap</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>29.077465</td>\n",
" <td>1.0060</td>\n",
" <td>volvo</td>\n",
" <td>benzyna</td>\n",
" <td>960.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>19.800027</td>\n",
" <td>1.0080</td>\n",
" <td>kia</td>\n",
" <td>diesel</td>\n",
" <td>418.8</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>27.916642</td>\n",
" <td>1.0075</td>\n",
" <td>toyota</td>\n",
" <td>diesel</td>\n",
" <td>420.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>32.976864</td>\n",
" <td>1.0075</td>\n",
" <td>skoda</td>\n",
" <td>diesel</td>\n",
" <td>480.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>38.932205</td>\n",
" <td>1.0060</td>\n",
" <td>renault</td>\n",
" <td>diesel</td>\n",
" <td>600.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>32.089045</td>\n",
" <td>1.0070</td>\n",
" <td>opel</td>\n",
" <td>diesel</td>\n",
" <td>390.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>31.997055</td>\n",
" <td>1.0065</td>\n",
" <td>mercedes-benz</td>\n",
" <td>diesel</td>\n",
" <td>900.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>26.138626</td>\n",
" <td>1.0075</td>\n",
" <td>ford</td>\n",
" <td>benzyna</td>\n",
" <td>300.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>38.142843</td>\n",
" <td>1.0015</td>\n",
" <td>seat</td>\n",
" <td>diesel</td>\n",
" <td>570.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>26.715448</td>\n",
" <td>1.0060</td>\n",
" <td>mercedes-benz</td>\n",
" <td>diesel</td>\n",
" <td>642.9</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" mileage year brand engine_type engine_cap\n",
"0 29.077465 1.0060 volvo benzyna 960.0\n",
"1 19.800027 1.0080 kia diesel 418.8\n",
"2 27.916642 1.0075 toyota diesel 420.0\n",
"3 32.976864 1.0075 skoda diesel 480.0\n",
"4 38.932205 1.0060 renault diesel 600.0\n",
"5 32.089045 1.0070 opel diesel 390.0\n",
"6 31.997055 1.0065 mercedes-benz diesel 900.0\n",
"7 26.138626 1.0075 ford benzyna 300.0\n",
"8 38.142843 1.0015 seat diesel 570.0\n",
"9 26.715448 1.0060 mercedes-benz diesel 642.9"
]
},
"execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head(10)"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>mileage</th>\n",
" <th>year</th>\n",
" <th>brand</th>\n",
" <th>engine_type</th>\n",
" <th>engine_cap</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>29.077465</td>\n",
" <td>1.0060</td>\n",
" <td>volvo</td>\n",
" <td>benzyna</td>\n",
" <td>960.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>19.800027</td>\n",
" <td>1.0080</td>\n",
" <td>kia</td>\n",
" <td>diesel</td>\n",
" <td>418.8</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>27.916642</td>\n",
" <td>1.0075</td>\n",
" <td>toyota</td>\n",
" <td>diesel</td>\n",
" <td>420.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>32.976864</td>\n",
" <td>1.0075</td>\n",
" <td>skoda</td>\n",
" <td>diesel</td>\n",
" <td>480.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>38.932205</td>\n",
" <td>1.0060</td>\n",
" <td>renault</td>\n",
" <td>diesel</td>\n",
" <td>600.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>47997</th>\n",
" <td>25.530471</td>\n",
" <td>1.0055</td>\n",
" <td>mini</td>\n",
" <td>benzyna</td>\n",
" <td>479.4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>47998</th>\n",
" <td>41.875698</td>\n",
" <td>1.0020</td>\n",
" <td>mercedes-benz</td>\n",
" <td>diesel</td>\n",
" <td>644.4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>47999</th>\n",
" <td>40.061463</td>\n",
" <td>1.0025</td>\n",
" <td>mercedes-benz</td>\n",
" <td>diesel</td>\n",
" <td>506.7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>48000</th>\n",
" <td>40.809827</td>\n",
" <td>1.0010</td>\n",
" <td>mercedes-benz</td>\n",
" <td>diesel</td>\n",
" <td>644.4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>48001</th>\n",
" <td>38.337702</td>\n",
" <td>1.0035</td>\n",
" <td>mercedes-benz</td>\n",
" <td>diesel</td>\n",
" <td>896.1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>47930 rows × 5 columns</p>\n",
"</div>"
],
"text/plain": [
" mileage year brand engine_type engine_cap\n",
"0 29.077465 1.0060 volvo benzyna 960.0\n",
"1 19.800027 1.0080 kia diesel 418.8\n",
"2 27.916642 1.0075 toyota diesel 420.0\n",
"3 32.976864 1.0075 skoda diesel 480.0\n",
"4 38.932205 1.0060 renault diesel 600.0\n",
"... ... ... ... ... ...\n",
"47997 25.530471 1.0055 mini benzyna 479.4\n",
"47998 41.875698 1.0020 mercedes-benz diesel 644.4\n",
"47999 40.061463 1.0025 mercedes-benz diesel 506.7\n",
"48000 40.809827 1.0010 mercedes-benz diesel 644.4\n",
"48001 38.337702 1.0035 mercedes-benz diesel 896.1\n",
"\n",
"[47930 rows x 5 columns]"
]
},
"execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Preprocessing danych\n",
"\n",
"## 1. Dane odstające\n",
"Na początku zostały usunięte dane odstające, takie jak auta, których cena jest poniżej tysiąca, lub których przebieg jest wyższy niż 900 000km."
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [],
"source": [
"Y_test = test_expected[0]\n",
"\n",
"\n",
"# Drop rows which have strange value\n",
"brands = df.brand.value_counts()[:35].index.tolist()\n",
"indexes = df_train[(df_train.price < 1000) & (df_train.price > 1)].index\n",
"df_train.drop(indexes, inplace=True)\n",
"\n",
"index = df_train[(df_train.mileage > 900000)].index\n",
"df_train.drop(index, inplace=True)\n",
"\n",
"Y_train = df_train[\"price\"]\n",
"df_train.drop(\"price\", axis=1, inplace=True)\n",
"\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 2. Normalizacja danych liczbowych\n",
"\n",
"Dane takie jak rok, przebieg czy pojemność silnika zostały znacząco zredukowane\n",
"\n",
"## 3. Lowercase nazw producentów\n",
"\n",
"Nazwy producentów zostały zapisane wyłącznie małymi literami\n",
"\n",
"## 4. Utworzenie 'dummies'\n",
"\n",
"Zostały utworzone kolumny dla każdej z marek przyjmujące wartość (0,1)\n",
"\n",
"## 5. Utworzenie wielomianiu stopnia 2\n",
"\n",
"Z wykorzystaniem biblioteki sklearn.preprocessing"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [],
"source": [
"def preprocess_data(df: DataFrame, brands: list) -> DataFrame:\n",
" \"\"\"Prepare dataset to linear regression\"\"\"\n",
"\n",
" df.brand = df.brand.apply(lambda x: x if x in brands else \"0\")\n",
" df[\"year\"] = df.year / 2000\n",
" df[\"mileage\"] = df.mileage ** 0.3\n",
" df[\"engine_cap\"] = df.engine_cap * 0.3\n",
" df[\"brand\"] = df[\"brand\"].str.lower()\n",
"\n",
" df = pd.get_dummies(df, columns=[\"brand\", \"engine_type\"])\n",
"\n",
" scaler = preprocessing.RobustScaler()\n",
" df[[\"mileage\", \"year\", \"engine_cap\", \"year\"]] = scaler.fit_transform(\n",
" df[[\"mileage\", \"year\", \"engine_cap\", \"year\"]]\n",
" )\n",
"\n",
" poly = PolynomialFeatures(2, interaction_only=True)\n",
" df = poly.fit_transform(df)\n",
"\n",
" return df"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [],
"source": [
"X_train = preprocess_data(df_train, brands)\n",
"X_test = preprocess_data(test, brands)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Regresja liniowa\n",
"\n",
"Implementacja regresji liniowej za pomocą biblioteki sklearn\n",
"\n",
"## RMSE: 22065.84\n",
"## MSE: 486901471.27"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"RMSE: 22065.843996457512\n",
"MSE: 486901471.276\n"
]
}
],
"source": [
"# Load model and fit data\n",
"lm_model = LinearRegression()\n",
"lm_model.fit(X_train, Y_train)\n",
"\n",
"# Predict\n",
"lr_test_predicted = lm_model.predict(X_test)\n",
"\n",
"# Predicted values to tsv\n",
"print(\"RMSE: \", mean_squared_error(Y_test, lr_test_predicted, squared=False))\n",
"print(\"MSE: \", mean_squared_error(Y_test, lr_test_predicted))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Sieć neuronowa (Keras)\n",
"\n",
"batch size: 64,\n",
"epochs: 100,\n",
"3 x ReLU\n",
"optimizer: adam,\n",
"loss: mean squared error\n",
"\n",
"\n",
"## RMSE: 18558.15\n",
"## MSE: 344404977.04"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/100\n",
"600/600 [==============================] - 5s 7ms/step - loss: 2673221721.0250 - mean_squared_error: 2673221721.0250 - val_loss: 551377856.0000 - val_mean_squared_error: 551377856.0000\n",
"Epoch 2/100\n",
"600/600 [==============================] - 3s 6ms/step - loss: 442345591.4276 - mean_squared_error: 442345591.4276 - val_loss: 423978976.0000 - val_mean_squared_error: 423978976.0000\n",
"Epoch 3/100\n",
"600/600 [==============================] - 3s 6ms/step - loss: 378405340.5923 - mean_squared_error: 378405340.5923 - val_loss: 378884192.0000 - val_mean_squared_error: 378884192.0000\n",
"Epoch 4/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 384769043.7271 - mean_squared_error: 384769043.7271 - val_loss: 357286848.0000 - val_mean_squared_error: 357286848.0000\n",
"Epoch 5/100\n",
"600/600 [==============================] - 4s 6ms/step - loss: 343957554.7155 - mean_squared_error: 343957554.7155 - val_loss: 340152512.0000 - val_mean_squared_error: 340152512.0000\n",
"Epoch 6/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 337887713.4376 - mean_squared_error: 337887713.4376 - val_loss: 331659872.0000 - val_mean_squared_error: 331659872.0000\n",
"Epoch 7/100\n",
"600/600 [==============================] - 4s 6ms/step - loss: 313163787.1281 - mean_squared_error: 313163787.1281 - val_loss: 323213504.0000 - val_mean_squared_error: 323213504.0000\n",
"Epoch 8/100\n",
"600/600 [==============================] - 4s 6ms/step - loss: 314339570.3428 - mean_squared_error: 314339570.3428 - val_loss: 317251488.0000 - val_mean_squared_error: 317251488.0000\n",
"Epoch 9/100\n",
"600/600 [==============================] - 5s 9ms/step - loss: 303178196.5524 - mean_squared_error: 303178196.5524 - val_loss: 314496736.0000 - val_mean_squared_error: 314496736.0000\n",
"Epoch 10/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 313794526.9351 - mean_squared_error: 313794526.9351 - val_loss: 310654176.0000 - val_mean_squared_error: 310654176.0000\n",
"Epoch 11/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 284679367.4542 - mean_squared_error: 284679367.4542 - val_loss: 304685248.0000 - val_mean_squared_error: 304685248.0000\n",
"Epoch 12/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 311546194.3161 - mean_squared_error: 311546194.3161 - val_loss: 304376256.0000 - val_mean_squared_error: 304376256.0000\n",
"Epoch 13/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 286383306.4892 - mean_squared_error: 286383306.4892 - val_loss: 303079392.0000 - val_mean_squared_error: 303079392.0000\n",
"Epoch 14/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 312419505.4110 - mean_squared_error: 312419505.4110 - val_loss: 296362720.0000 - val_mean_squared_error: 296362720.0000\n",
"Epoch 15/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 281224970.5957 - mean_squared_error: 281224970.5957 - val_loss: 295127040.0000 - val_mean_squared_error: 295127040.0000\n",
"Epoch 16/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 300456786.4759 - mean_squared_error: 300456786.4759 - val_loss: 291579264.0000 - val_mean_squared_error: 291579264.0000\n",
"Epoch 17/100\n",
"600/600 [==============================] - 4s 6ms/step - loss: 271273312.1864 - mean_squared_error: 271273312.1864 - val_loss: 293092064.0000 - val_mean_squared_error: 293092064.0000\n",
"Epoch 18/100\n",
"600/600 [==============================] - 4s 6ms/step - loss: 274466717.5241 - mean_squared_error: 274466717.5241 - val_loss: 291955424.0000 - val_mean_squared_error: 291955424.0000\n",
"Epoch 19/100\n",
"600/600 [==============================] - 4s 6ms/step - loss: 280078536.3328 - mean_squared_error: 280078536.3328 - val_loss: 286574528.0000 - val_mean_squared_error: 286574528.0000\n",
"Epoch 20/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 283455574.6290 - mean_squared_error: 283455574.6290 - val_loss: 283341472.0000 - val_mean_squared_error: 283341472.0000\n",
"Epoch 21/100\n",
"600/600 [==============================] - 4s 6ms/step - loss: 269008367.3078 - mean_squared_error: 269008367.3078 - val_loss: 287479776.0000 - val_mean_squared_error: 287479776.0000\n",
"Epoch 22/100\n",
"600/600 [==============================] - 4s 6ms/step - loss: 285307228.4326 - mean_squared_error: 285307228.4326 - val_loss: 281901632.0000 - val_mean_squared_error: 281901632.0000\n",
"Epoch 23/100\n",
"600/600 [==============================] - 4s 6ms/step - loss: 270041985.1448 - mean_squared_error: 270041985.1448 - val_loss: 285430688.0000 - val_mean_squared_error: 285430688.0000\n",
"Epoch 24/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 287381889.8902 - mean_squared_error: 287381889.8902 - val_loss: 283002208.0000 - val_mean_squared_error: 283002208.0000\n",
"Epoch 25/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 290092397.6839 - mean_squared_error: 290092397.6839 - val_loss: 281590592.0000 - val_mean_squared_error: 281590592.0000\n",
"Epoch 26/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 287577090.5291 - mean_squared_error: 287577090.5291 - val_loss: 277902464.0000 - val_mean_squared_error: 277902464.0000\n",
"Epoch 27/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 272385114.1165 - mean_squared_error: 272385114.1165 - val_loss: 280177056.0000 - val_mean_squared_error: 280177056.0000\n",
"Epoch 28/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 257438328.8785 - mean_squared_error: 257438328.8785 - val_loss: 284091104.0000 - val_mean_squared_error: 284091104.0000\n",
"Epoch 29/100\n",
"600/600 [==============================] - 3s 6ms/step - loss: 276722888.6256 - mean_squared_error: 276722888.6256 - val_loss: 277816032.0000 - val_mean_squared_error: 277816032.0000\n",
"Epoch 30/100\n",
"600/600 [==============================] - 3s 6ms/step - loss: 271698972.8586 - mean_squared_error: 271698972.8586 - val_loss: 281744256.0000 - val_mean_squared_error: 281744256.0000\n",
"Epoch 31/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 277800460.3261 - mean_squared_error: 277800460.3261 - val_loss: 275767552.0000 - val_mean_squared_error: 275767552.0000\n",
"Epoch 32/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 255387858.4093 - mean_squared_error: 255387858.4093 - val_loss: 274004512.0000 - val_mean_squared_error: 274004512.0000\n",
"Epoch 33/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 267013800.2263 - mean_squared_error: 267013800.2263 - val_loss: 274496832.0000 - val_mean_squared_error: 274496832.0000\n",
"Epoch 34/100\n",
"600/600 [==============================] - 4s 6ms/step - loss: 270699375.3611 - mean_squared_error: 270699375.3611 - val_loss: 276478944.0000 - val_mean_squared_error: 276478944.0000\n",
"Epoch 35/100\n",
"600/600 [==============================] - 4s 6ms/step - loss: 279694474.7288 - mean_squared_error: 279694474.7288 - val_loss: 279028160.0000 - val_mean_squared_error: 279028160.0000\n",
"Epoch 36/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 270710719.1747 - mean_squared_error: 270710719.1747 - val_loss: 273949600.0000 - val_mean_squared_error: 273949600.0000\n",
"Epoch 37/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 272804902.7354 - mean_squared_error: 272804902.7354 - val_loss: 274979104.0000 - val_mean_squared_error: 274979104.0000\n",
"Epoch 38/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 254984751.6805 - mean_squared_error: 254984751.6805 - val_loss: 278099008.0000 - val_mean_squared_error: 278099008.0000\n",
"Epoch 39/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 263644632.1597 - mean_squared_error: 263644632.1597 - val_loss: 275570400.0000 - val_mean_squared_error: 275570400.0000\n",
"Epoch 40/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 283981970.5824 - mean_squared_error: 283981970.5824 - val_loss: 269600896.0000 - val_mean_squared_error: 269600896.0000\n",
"Epoch 41/100\n",
"600/600 [==============================] - 4s 6ms/step - loss: 263011782.5225 - mean_squared_error: 263011782.5225 - val_loss: 270043744.0000 - val_mean_squared_error: 270043744.0000\n",
"Epoch 42/100\n",
"600/600 [==============================] - 4s 6ms/step - loss: 275432014.8286 - mean_squared_error: 275432014.8286 - val_loss: 268776480.0000 - val_mean_squared_error: 268776480.0000\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 43/100\n",
"600/600 [==============================] - 3s 6ms/step - loss: 260651440.1864 - mean_squared_error: 260651440.1864 - val_loss: 275194144.0000 - val_mean_squared_error: 275194144.0000\n",
"Epoch 44/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 257748764.5125 - mean_squared_error: 257748764.5125 - val_loss: 270911072.0000 - val_mean_squared_error: 270911072.0000\n",
"Epoch 45/100\n",
"600/600 [==============================] - 3s 6ms/step - loss: 266450056.8918 - mean_squared_error: 266450056.8918 - val_loss: 270361472.0000 - val_mean_squared_error: 270361472.0000\n",
"Epoch 46/100\n",
"600/600 [==============================] - 3s 5ms/step - loss: 267280017.8369 - mean_squared_error: 267280017.8369 - val_loss: 268170224.0000 - val_mean_squared_error: 268170224.0000\n",
"Epoch 47/100\n",
"600/600 [==============================] - 4s 6ms/step - loss: 270953393.1048 - mean_squared_error: 270953393.1048 - val_loss: 266962048.0000 - val_mean_squared_error: 266962048.0000\n",
"Epoch 48/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 261569597.8436 - mean_squared_error: 261569597.8436 - val_loss: 270642752.0000 - val_mean_squared_error: 270642752.0000\n",
"Epoch 49/100\n",
"600/600 [==============================] - 5s 9ms/step - loss: 252863808.0799 - mean_squared_error: 252863808.0799 - val_loss: 264875584.0000 - val_mean_squared_error: 264875584.0000\n",
"Epoch 50/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 269732835.3677 - mean_squared_error: 269732835.3677 - val_loss: 265078368.0000 - val_mean_squared_error: 265078368.0000\n",
"Epoch 51/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 277777046.5225 - mean_squared_error: 277777046.5225 - val_loss: 265569424.0000 - val_mean_squared_error: 265569424.0000\n",
"Epoch 52/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 259421935.3611 - mean_squared_error: 259421935.3611 - val_loss: 263121728.0000 - val_mean_squared_error: 263121728.0000\n",
"Epoch 53/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 246818920.4126 - mean_squared_error: 246818920.4126 - val_loss: 268283376.0000 - val_mean_squared_error: 268283376.0000\n",
"Epoch 54/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 262059519.1747 - mean_squared_error: 262059519.1747 - val_loss: 264587712.0000 - val_mean_squared_error: 264587712.0000\n",
"Epoch 55/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 251146320.5857 - mean_squared_error: 251146320.5857 - val_loss: 264188048.0000 - val_mean_squared_error: 264188048.0000\n",
"Epoch 56/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 277728213.8569 - mean_squared_error: 277728213.8569 - val_loss: 265315792.0000 - val_mean_squared_error: 265315792.0000\n",
"Epoch 57/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 273021954.3694 - mean_squared_error: 273021954.3694 - val_loss: 265453232.0000 - val_mean_squared_error: 265453232.0000\n",
"Epoch 58/100\n",
"600/600 [==============================] - 5s 7ms/step - loss: 235758602.8619 - mean_squared_error: 235758602.8619 - val_loss: 267418880.0000 - val_mean_squared_error: 267418880.0000\n",
"Epoch 59/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 253989512.0932 - mean_squared_error: 253989512.0932 - val_loss: 263675520.0000 - val_mean_squared_error: 263675520.0000\n",
"Epoch 60/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 262297644.0067 - mean_squared_error: 262297644.0067 - val_loss: 260217264.0000 - val_mean_squared_error: 260217264.0000\n",
"Epoch 61/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 265082348.2596 - mean_squared_error: 265082348.2596 - val_loss: 262431664.0000 - val_mean_squared_error: 262431664.0000\n",
"Epoch 62/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 257870115.1681 - mean_squared_error: 257870115.1681 - val_loss: 262881312.0000 - val_mean_squared_error: 262881312.0000\n",
"Epoch 63/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 240457727.4143 - mean_squared_error: 240457727.4143 - val_loss: 261733392.0000 - val_mean_squared_error: 261733392.0000\n",
"Epoch 64/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 277940927.2013 - mean_squared_error: 277940927.2013 - val_loss: 260641392.0000 - val_mean_squared_error: 260641392.0000\n",
"Epoch 65/100\n",
"600/600 [==============================] - 5s 9ms/step - loss: 243245328.8120 - mean_squared_error: 243245328.8120 - val_loss: 266007856.0000 - val_mean_squared_error: 266007856.0000\n",
"Epoch 66/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 280276759.2679 - mean_squared_error: 280276759.2679 - val_loss: 260283456.0000 - val_mean_squared_error: 260283456.0000\n",
"Epoch 67/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 256323983.0948 - mean_squared_error: 256323983.0948 - val_loss: 260369344.0000 - val_mean_squared_error: 260369344.0000\n",
"Epoch 68/100\n",
"600/600 [==============================] - 6s 10ms/step - loss: 257920354.0499 - mean_squared_error: 257920354.0499 - val_loss: 259491872.0000 - val_mean_squared_error: 259491872.0000\n",
"Epoch 69/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 248803245.8436 - mean_squared_error: 248803245.8436 - val_loss: 260577376.0000 - val_mean_squared_error: 260577376.0000\n",
"Epoch 70/100\n",
"600/600 [==============================] - 5s 9ms/step - loss: 262326159.4676 - mean_squared_error: 262326159.4676 - val_loss: 261333040.0000 - val_mean_squared_error: 261333040.0000\n",
"Epoch 71/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 244443427.6473 - mean_squared_error: 244443427.6473 - val_loss: 260864640.0000 - val_mean_squared_error: 260864640.0000\n",
"Epoch 72/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 251957369.0782 - mean_squared_error: 251957369.0782 - val_loss: 260814608.0000 - val_mean_squared_error: 260814608.0000\n",
"Epoch 73/100\n",
"600/600 [==============================] - 5s 7ms/step - loss: 258517712.4792 - mean_squared_error: 258517712.4792 - val_loss: 258114464.0000 - val_mean_squared_error: 258114464.0000\n",
"Epoch 74/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 219879441.5308 - mean_squared_error: 219879441.5308 - val_loss: 262360560.0000 - val_mean_squared_error: 262360560.0000\n",
"Epoch 75/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 260794823.4143 - mean_squared_error: 260794823.4143 - val_loss: 256498032.0000 - val_mean_squared_error: 256498032.0000\n",
"Epoch 76/100\n",
"600/600 [==============================] - 5s 9ms/step - loss: 239282565.3511 - mean_squared_error: 239282565.3511 - val_loss: 262098640.0000 - val_mean_squared_error: 262098640.0000\n",
"Epoch 77/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 257229255.3478 - mean_squared_error: 257229255.3478 - val_loss: 259628224.0000 - val_mean_squared_error: 259628224.0000\n",
"Epoch 78/100\n",
"600/600 [==============================] - 5s 9ms/step - loss: 244059795.5541 - mean_squared_error: 244059795.5541 - val_loss: 259398896.0000 - val_mean_squared_error: 259398896.0000\n",
"Epoch 79/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 255108445.9767 - mean_squared_error: 255108445.9767 - val_loss: 259564784.0000 - val_mean_squared_error: 259564784.0000\n",
"Epoch 80/100\n",
"600/600 [==============================] - 5s 9ms/step - loss: 252858985.0250 - mean_squared_error: 252858985.0250 - val_loss: 261315536.0000 - val_mean_squared_error: 261315536.0000\n",
"Epoch 81/100\n",
"600/600 [==============================] - 6s 9ms/step - loss: 251545596.1664 - mean_squared_error: 251545596.1664 - val_loss: 259559184.0000 - val_mean_squared_error: 259559184.0000\n",
"Epoch 82/100\n",
"600/600 [==============================] - 6s 10ms/step - loss: 253448548.1464 - mean_squared_error: 253448548.1464 - val_loss: 257081360.0000 - val_mean_squared_error: 257081360.0000\n",
"Epoch 83/100\n",
"600/600 [==============================] - 7s 11ms/step - loss: 223692804.4592 - mean_squared_error: 223692804.4592 - val_loss: 260599392.0000 - val_mean_squared_error: 260599392.0000\n",
"Epoch 84/100\n",
"600/600 [==============================] - 6s 10ms/step - loss: 238604269.9767 - mean_squared_error: 238604269.9767 - val_loss: 259515504.0000 - val_mean_squared_error: 259515504.0000\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 85/100\n",
"600/600 [==============================] - 4s 6ms/step - loss: 239357600.3993 - mean_squared_error: 239357600.3993 - val_loss: 258469696.0000 - val_mean_squared_error: 258469696.0000\n",
"Epoch 86/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 250585435.0483 - mean_squared_error: 250585435.0483 - val_loss: 257148032.0000 - val_mean_squared_error: 257148032.0000\n",
"Epoch 87/100\n",
"600/600 [==============================] - 4s 6ms/step - loss: 241135506.1564 - mean_squared_error: 241135506.1564 - val_loss: 255790992.0000 - val_mean_squared_error: 255790992.0000\n",
"Epoch 88/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 236478667.7005 - mean_squared_error: 236478667.7005 - val_loss: 255462960.0000 - val_mean_squared_error: 255462960.0000\n",
"Epoch 89/100\n",
"600/600 [==============================] - 4s 7ms/step - loss: 255623276.9917 - mean_squared_error: 255623276.9917 - val_loss: 256298672.0000 - val_mean_squared_error: 256298672.0000\n",
"Epoch 90/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 225196806.3095 - mean_squared_error: 225196806.3095 - val_loss: 258884368.0000 - val_mean_squared_error: 258884368.0000\n",
"Epoch 91/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 240176409.9700 - mean_squared_error: 240176409.9700 - val_loss: 257321488.0000 - val_mean_squared_error: 257321488.0000\n",
"Epoch 92/100\n",
"600/600 [==============================] - 5s 9ms/step - loss: 239258905.3710 - mean_squared_error: 239258905.3710 - val_loss: 260538288.0000 - val_mean_squared_error: 260538288.0000\n",
"Epoch 93/100\n",
"600/600 [==============================] - 5s 9ms/step - loss: 245292192.2130 - mean_squared_error: 245292192.2130 - val_loss: 255793472.0000 - val_mean_squared_error: 255793472.0000\n",
"Epoch 94/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 243730631.4542 - mean_squared_error: 243730631.4542 - val_loss: 255217168.0000 - val_mean_squared_error: 255217168.0000\n",
"Epoch 95/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 241191757.3378 - mean_squared_error: 241191757.3378 - val_loss: 258455520.0000 - val_mean_squared_error: 258455520.0000\n",
"Epoch 96/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 234345852.6057 - mean_squared_error: 234345852.6057 - val_loss: 259143584.0000 - val_mean_squared_error: 259143584.0000\n",
"Epoch 97/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 237245952.2130 - mean_squared_error: 237245952.2130 - val_loss: 256133552.0000 - val_mean_squared_error: 256133552.0000\n",
"Epoch 98/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 246080581.8835 - mean_squared_error: 246080581.8835 - val_loss: 255931216.0000 - val_mean_squared_error: 255931216.0000\n",
"Epoch 99/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 259659058.3428 - mean_squared_error: 259659058.3428 - val_loss: 253970368.0000 - val_mean_squared_error: 253970368.0000\n",
"Epoch 100/100\n",
"600/600 [==============================] - 5s 8ms/step - loss: 251161536.1864 - mean_squared_error: 251161536.1864 - val_loss: 253605840.0000 - val_mean_squared_error: 253605840.0000\n",
"RMSE: 18558.15122927888\n",
"MSE: 344404977.04878515\n"
]
}
],
"source": [
"input_layer = Input(shape=(X_train.shape[1]))\n",
"dense_layer_1 = Dense(100, activation='relu')(input_layer)\n",
"dense_layer_2 = Dense(50, activation='relu')(dense_layer_1)\n",
"dense_layer_3 = Dense(25, activation='relu')(dense_layer_2)\n",
"output = Dense(1)(dense_layer_3)\n",
"\n",
"model = Model(inputs=input_layer, outputs=output)\n",
"model.compile(loss=\"mean_squared_error\", optimizer=\"adam\", metrics=[\"mean_squared_error\"])\n",
"\n",
"\n",
"model.fit(X_train, Y_train, batch_size=64, epochs=100, verbose=1, validation_split=0.2)\n",
"y_pred = model.predict(X_test)\n",
"\n",
"print(f\"RMSE: {mean_squared_error(Y_test, y_pred, squared=False)}\")\n",
"print(f\"MSE: {mean_squared_error(Y_test, y_pred)}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Gradient Boosting Regressor\n",
"\n",
"Regresja liniowa z wykorzystaniem technik wzmocnienia gradientowego z wykorzystaniem \n",
"sklearn\n",
"\n",
"## RMSE: 19705.96\n",
"## MSE: 388324934.97"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"RMSE: 19705.961914565338\n",
"MSE: 388324934.9782996\n"
]
}
],
"source": [
"\"\"\"\n",
"Gradient Boosting Regressor\n",
"\"\"\"\n",
"\n",
"model = ensemble.GradientBoostingRegressor()\n",
"model.fit(X_train, Y_train)\n",
"\n",
"gradient_predicted = model.predict(X_test)\n",
"print(f\"RMSE: {mean_squared_error(Y_test, gradient_predicted, squared=False)}\")\n",
"print(f\"MSE: {mean_squared_error(Y_test, gradient_predicted)}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Podsumowanie\n",
"\n",
"## 1. Sieć neuronowa \n",
"## 2. Gradient Boosting Regressor\n",
"## 3. Regresja liniowa\n",
"\n",
"Najlepsze wyniki zostały osiągnięte przez model sieci neuronowej. Na drugim miejscu plasuje się metoda wzmocnienia gradientowego, a na trzecim regresja liniowa, wynika to z użycia wzmocnienia gradientowego, który pomaga wskazać kierunek, w którym nasz model ma się poprawiać."
]
}
],
"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": "3.9.5"
}
},
"nbformat": 4,
"nbformat_minor": 1
}

177
requirements.txt Normal file
View File

@ -0,0 +1,177 @@
# This file may be used to create an environment using:
# $ conda create --name <env> --file <this file>
# platform: linux-64
_libgcc_mutex=0.1=main
_openmp_mutex=4.5=1_gnu
_tflow_select=2.3.0=mkl
absl-py=0.12.0=py39h06a4308_0
aiohttp=3.7.4=py39h27cfd23_1
argon2-cffi=20.1.0=py39h27cfd23_1
astor=0.8.1=py39h06a4308_0
astunparse=1.6.3=py_0
async-timeout=3.0.1=py39h06a4308_0
async_generator=1.10=pyhd3eb1b0_0
attrs=21.2.0=pyhd3eb1b0_0
backcall=0.2.0=pyhd3eb1b0_0
blas=1.0=mkl
bleach=3.3.0=pyhd3eb1b0_0
blinker=1.4=py39h06a4308_0
brotlipy=0.7.0=py39h27cfd23_1003
c-ares=1.17.1=h27cfd23_0
ca-certificates=2021.5.25=h06a4308_1
cachetools=4.2.2=pyhd3eb1b0_0
certifi=2021.5.30=py39h06a4308_0
cffi=1.14.5=py39h261ae71_0
chardet=3.0.4=py39h06a4308_1003
click=8.0.1=pyhd3eb1b0_0
coverage=5.5=py39h27cfd23_2
cryptography=3.4.7=py39hd23ed53_0
cython=0.29.23=py39h2531618_0
daal4py=2021.2.2=py39ha9443f7_0
dal=2021.2.2=h06a4308_389
dbus=1.13.18=hb2f20db_0
decorator=5.0.9=pyhd3eb1b0_0
defusedxml=0.7.1=pyhd3eb1b0_0
entrypoints=0.3=py39h06a4308_0
expat=2.4.1=h2531618_2
fontconfig=2.13.1=h6c09931_0
freetype=2.10.4=h5ab3b9f_0
gast=0.4.0=py_0
glib=2.68.2=h36276a3_0
google-auth=1.30.1=pyhd3eb1b0_0
google-auth-oauthlib=0.4.4=pyhd3eb1b0_0
google-pasta=0.2.0=py_0
grpcio=1.36.1=py39h2157cd5_1
gst-plugins-base=1.14.0=h8213a91_2
gstreamer=1.14.0=h28cd5cc_2
h5py=2.10.0=py39hec9cf62_0
hdf5=1.10.6=hb1b8bf9_0
icu=58.2=he6710b0_3
idna=2.10=pyhd3eb1b0_0
importlib-metadata=3.10.0=py39h06a4308_0
importlib_metadata=3.10.0=hd3eb1b0_0
intel-openmp=2021.2.0=h06a4308_610
ipykernel=5.3.4=py39hb070fc8_0
ipython=7.22.0=py39hb070fc8_0
ipython_genutils=0.2.0=pyhd3eb1b0_1
ipywidgets=7.6.3=pyhd3eb1b0_1
jedi=0.17.2=py39h06a4308_1
jinja2=3.0.0=pyhd3eb1b0_0
joblib=1.0.1=pyhd3eb1b0_0
jpeg=9b=h024ee3a_2
jsonschema=3.2.0=py_2
jupyter=1.0.0=py39h06a4308_7
jupyter_client=6.1.12=pyhd3eb1b0_0
jupyter_console=6.4.0=pyhd3eb1b0_0
jupyter_core=4.7.1=py39h06a4308_0
jupyterlab_pygments=0.1.2=py_0
jupyterlab_widgets=1.0.0=pyhd3eb1b0_1
keras-preprocessing=1.1.2=pyhd3eb1b0_0
ld_impl_linux-64=2.35.1=h7274673_9
libffi=3.3=he6710b0_2
libgcc-ng=9.3.0=h5101ec6_17
libgfortran-ng=7.5.0=ha8ba4b0_17
libgfortran4=7.5.0=ha8ba4b0_17
libgomp=9.3.0=h5101ec6_17
libpng=1.6.37=hbc83047_0
libprotobuf=3.14.0=h8c45485_0
libsodium=1.0.18=h7b6447c_0
libstdcxx-ng=9.3.0=hd4cf53a_17
libuuid=1.0.3=h1bed415_2
libxcb=1.14=h7b6447c_0
libxml2=2.9.10=hb55368b_3
markdown=3.3.4=py39h06a4308_0
markupsafe=2.0.1=py39h27cfd23_0
mistune=0.8.4=py39h27cfd23_1000
mkl=2021.2.0=h06a4308_296
mkl-service=2.3.0=py39h27cfd23_1
mkl_fft=1.3.0=py39h42c9631_2
mkl_random=1.2.1=py39ha9443f7_2
mpi=1.0=mpich
mpich=3.3.2=hc856adb_0
multidict=5.1.0=py39h27cfd23_2
nbclient=0.5.3=pyhd3eb1b0_0
nbconvert=6.0.7=py39h06a4308_0
nbformat=5.1.3=pyhd3eb1b0_0
ncurses=6.2=he6710b0_1
nest-asyncio=1.5.1=pyhd3eb1b0_0
notebook=6.4.0=py39h06a4308_0
numpy=1.20.2=py39h2d18471_0
numpy-base=1.20.2=py39hfae3a4d_0
oauthlib=3.1.1=pyhd3eb1b0_0
openssl=1.1.1k=h27cfd23_0
opt_einsum=3.3.0=pyhd3eb1b0_1
packaging=20.9=pyhd3eb1b0_0
pandas=1.2.4=py39h2531618_0
pandoc=2.12=h06a4308_0
pandocfilters=1.4.3=py39h06a4308_1
parso=0.7.0=py_0
pcre=8.44=he6710b0_0
pexpect=4.8.0=pyhd3eb1b0_3
pickleshare=0.7.5=pyhd3eb1b0_1003
pip=21.1.2=py39h06a4308_0
prometheus_client=0.11.0=pyhd3eb1b0_0
prompt-toolkit=3.0.17=pyh06a4308_0
prompt_toolkit=3.0.17=hd3eb1b0_0
protobuf=3.14.0=py39h2531618_1
ptyprocess=0.7.0=pyhd3eb1b0_2
pyasn1=0.4.8=py_0
pyasn1-modules=0.2.8=py_0
pycparser=2.20=py_2
pygments=2.9.0=pyhd3eb1b0_0
pyjwt=2.1.0=py39h06a4308_0
pyopenssl=20.0.1=pyhd3eb1b0_1
pyparsing=2.4.7=pyhd3eb1b0_0
pyqt=5.9.2=py39h2531618_6
pyrsistent=0.17.3=py39h27cfd23_0
pysocks=1.7.1=py39h06a4308_0
python=3.9.5=h12debd9_4
python-dateutil=2.8.1=pyhd3eb1b0_0
python-flatbuffers=1.12=pyhd3eb1b0_0
pytz=2021.1=pyhd3eb1b0_0
pyzmq=20.0.0=py39h2531618_1
qt=5.9.7=h5867ecd_1
qtconsole=5.1.0=pyhd3eb1b0_0
qtpy=1.9.0=py_0
readline=8.1=h27cfd23_0
requests=2.25.1=pyhd3eb1b0_0
requests-oauthlib=1.3.0=py_0
rsa=4.7.2=pyhd3eb1b0_1
scikit-learn=0.24.2=py39ha9443f7_0
scikit-learn-intelex=2021.2.2=py39h06a4308_0
scipy=1.6.2=py39had2a1c9_1
send2trash=1.5.0=pyhd3eb1b0_1
setuptools=52.0.0=py39h06a4308_0
sip=4.19.13=py39h2531618_0
six=1.15.0=py39h06a4308_0
sqlite=3.35.4=hdfb4753_0
tbb=2021.2.0=hff7bd54_0
tensorboard=2.4.0=pyhc547734_0
tensorboard-plugin-wit=1.6.0=py_0
tensorflow=2.4.1=mkl_py39h4683426_0
tensorflow-addons=0.13.0=pypi_0
tensorflow-base=2.4.1=mkl_py39h43e0292_0
tensorflow-estimator=2.5.0=pyh7b7c402_0
termcolor=1.1.0=py39h06a4308_1
terminado=0.9.4=py39h06a4308_0
testpath=0.4.4=pyhd3eb1b0_0
threadpoolctl=2.1.0=pyh5ca1d4c_0
tk=8.6.10=hbc83047_0
tornado=6.1=py39h27cfd23_0
traitlets=5.0.5=pyhd3eb1b0_0
typeguard=2.12.1=pypi_0
typing-extensions=3.7.4.3=hd3eb1b0_0
typing_extensions=3.7.4.3=pyh06a4308_0
tzdata=2020f=h52ac0ba_0
urllib3=1.26.4=pyhd3eb1b0_0
wcwidth=0.2.5=py_0
webencodings=0.5.1=py39h06a4308_1
werkzeug=1.0.1=pyhd3eb1b0_0
wheel=0.36.2=pyhd3eb1b0_0
widgetsnbextension=3.5.1=py39h06a4308_0
wrapt=1.12.1=py39he8ac12f_1
xz=5.2.5=h7b6447c_0
yarl=1.6.3=py39h27cfd23_0
zeromq=4.3.4=h2531618_0
zipp=3.4.1=pyhd3eb1b0_0
zlib=1.2.11=h7b6447c_3

48002
train/train.tsv Normal file

File diff suppressed because it is too large Load Diff