{ "cells": [ { "cell_type": "code", "execution_count": 101, "id": "ddcaf12b", "metadata": {}, "outputs": [], "source": [ "# Import required libraries\n", "import pandas as pd\n", "import numpy as np \n", "import matplotlib.pyplot as plt\n", "import sklearn\n", "\n", "# Import necessary modules\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.metrics import mean_squared_error\n", "from math import sqrt\n", "\n", "# Keras specific\n", "import keras\n", "from keras.models import Sequential\n", "from keras.layers import Dense" ] }, { "cell_type": "code", "execution_count": 102, "id": "70e3b6e3", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "9360" ] }, "execution_count": 102, "metadata": {}, "output_type": "execute_result" } ], "source": [ "in_columns = ['id_stacji', 'nazwa_stacji', 'typ_zbioru', 'rok', 'miesiąc']\n", "\n", "df = pd.read_csv('train/in.tsv', names=in_columns, sep='\\t')\n", "df2 = pd.read_csv('dev-0/in.tsv', names=in_columns, sep='\\t')\n", "df = pd.concat([df, df2])\n", "len(df)" ] }, { "cell_type": "code", "execution_count": 103, "id": "44f404d6", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "720" ] }, "execution_count": 103, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_test = pd.read_csv('test-A/in.tsv', names=in_columns, sep='\\t')\n", "len(df_test)" ] }, { "cell_type": "code", "execution_count": 104, "id": "c760402a", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "10080" ] }, "execution_count": 104, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df = pd.concat([df,df_test])\n", "len(df)" ] }, { "cell_type": "code", "execution_count": 105, "id": "06f39e15", "metadata": {}, "outputs": [], "source": [ "df = df.drop(['nazwa_stacji','typ_zbioru'], axis=1)" ] }, { "cell_type": "code", "execution_count": 106, "id": "91c047f6", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
id_stacji_249180010id_stacji_249190560id_stacji_249200370id_stacji_249200490id_stacji_249220150id_stacji_249220180id_stacji_250190160id_stacji_250190390id_stacji_250210130id_stacji_251170090...miesiąc_3miesiąc_4miesiąc_5miesiąc_6miesiąc_7miesiąc_8miesiąc_9miesiąc_10miesiąc_11miesiąc_12
01000000000...0000000000
11000000000...0000000000
21000000000...1000000000
31000000000...0100000000
41000000000...0010000000
..................................................................
7150000000000...0000010000
7160000000000...0000001000
7170000000000...0000000100
7180000000000...0000000010
7190000000000...0000000001
\n", "

10080 rows × 73 columns

\n", "
" ], "text/plain": [ " id_stacji_249180010 id_stacji_249190560 id_stacji_249200370 \\\n", "0 1 0 0 \n", "1 1 0 0 \n", "2 1 0 0 \n", "3 1 0 0 \n", "4 1 0 0 \n", ".. ... ... ... \n", "715 0 0 0 \n", "716 0 0 0 \n", "717 0 0 0 \n", "718 0 0 0 \n", "719 0 0 0 \n", "\n", " id_stacji_249200490 id_stacji_249220150 id_stacji_249220180 \\\n", "0 0 0 0 \n", "1 0 0 0 \n", "2 0 0 0 \n", "3 0 0 0 \n", "4 0 0 0 \n", ".. ... ... ... \n", "715 0 0 0 \n", "716 0 0 0 \n", "717 0 0 0 \n", "718 0 0 0 \n", "719 0 0 0 \n", "\n", " id_stacji_250190160 id_stacji_250190390 id_stacji_250210130 \\\n", "0 0 0 0 \n", "1 0 0 0 \n", "2 0 0 0 \n", "3 0 0 0 \n", "4 0 0 0 \n", ".. ... ... ... \n", "715 0 0 0 \n", "716 0 0 0 \n", "717 0 0 0 \n", "718 0 0 0 \n", "719 0 0 0 \n", "\n", " id_stacji_251170090 ... miesiąc_3 miesiąc_4 miesiąc_5 miesiąc_6 \\\n", "0 0 ... 0 0 0 0 \n", "1 0 ... 0 0 0 0 \n", "2 0 ... 1 0 0 0 \n", "3 0 ... 0 1 0 0 \n", "4 0 ... 0 0 1 0 \n", ".. ... ... ... ... ... ... \n", "715 0 ... 0 0 0 0 \n", "716 0 ... 0 0 0 0 \n", "717 0 ... 0 0 0 0 \n", "718 0 ... 0 0 0 0 \n", "719 0 ... 0 0 0 0 \n", "\n", " miesiąc_7 miesiąc_8 miesiąc_9 miesiąc_10 miesiąc_11 miesiąc_12 \n", "0 0 0 0 0 0 0 \n", "1 0 0 0 0 0 0 \n", "2 0 0 0 0 0 0 \n", "3 0 0 0 0 0 0 \n", "4 0 0 0 0 0 0 \n", ".. ... ... ... ... ... ... \n", "715 0 1 0 0 0 0 \n", "716 0 0 1 0 0 0 \n", "717 0 0 0 1 0 0 \n", "718 0 0 0 0 1 0 \n", "719 0 0 0 0 0 1 \n", "\n", "[10080 rows x 73 columns]" ] }, "execution_count": 106, "metadata": {}, "output_type": "execute_result" } ], "source": [ "x = pd.get_dummies(df,columns = ['id_stacji','rok','miesiąc'])\n", "x" ] }, { "cell_type": "code", "execution_count": 107, "id": "037f1315", "metadata": {}, "outputs": [], "source": [ "x = x.iloc[:-720]" ] }, { "cell_type": "code", "execution_count": 108, "id": "e03bae07", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
id_stacji_249180010id_stacji_249190560id_stacji_249200370id_stacji_249200490id_stacji_249220150id_stacji_249220180id_stacji_250190160id_stacji_250190390id_stacji_250210130id_stacji_251170090...miesiąc_3miesiąc_4miesiąc_5miesiąc_6miesiąc_7miesiąc_8miesiąc_9miesiąc_10miesiąc_11miesiąc_12
01000000000...0000000000
11000000000...0000000000
21000000000...1000000000
31000000000...0100000000
41000000000...0010000000
..................................................................
5950000000000...0000010000
5960000000000...0000001000
5970000000000...0000000100
5980000000000...0000000010
5990000000000...0000000001
\n", "

9360 rows × 73 columns

\n", "
" ], "text/plain": [ " id_stacji_249180010 id_stacji_249190560 id_stacji_249200370 \\\n", "0 1 0 0 \n", "1 1 0 0 \n", "2 1 0 0 \n", "3 1 0 0 \n", "4 1 0 0 \n", ".. ... ... ... \n", "595 0 0 0 \n", "596 0 0 0 \n", "597 0 0 0 \n", "598 0 0 0 \n", "599 0 0 0 \n", "\n", " id_stacji_249200490 id_stacji_249220150 id_stacji_249220180 \\\n", "0 0 0 0 \n", "1 0 0 0 \n", "2 0 0 0 \n", "3 0 0 0 \n", "4 0 0 0 \n", ".. ... ... ... \n", "595 0 0 0 \n", "596 0 0 0 \n", "597 0 0 0 \n", "598 0 0 0 \n", "599 0 0 0 \n", "\n", " id_stacji_250190160 id_stacji_250190390 id_stacji_250210130 \\\n", "0 0 0 0 \n", "1 0 0 0 \n", "2 0 0 0 \n", "3 0 0 0 \n", "4 0 0 0 \n", ".. ... ... ... \n", "595 0 0 0 \n", "596 0 0 0 \n", "597 0 0 0 \n", "598 0 0 0 \n", "599 0 0 0 \n", "\n", " id_stacji_251170090 ... miesiąc_3 miesiąc_4 miesiąc_5 miesiąc_6 \\\n", "0 0 ... 0 0 0 0 \n", "1 0 ... 0 0 0 0 \n", "2 0 ... 1 0 0 0 \n", "3 0 ... 0 1 0 0 \n", "4 0 ... 0 0 1 0 \n", ".. ... ... ... ... ... ... \n", "595 0 ... 0 0 0 0 \n", "596 0 ... 0 0 0 0 \n", "597 0 ... 0 0 0 0 \n", "598 0 ... 0 0 0 0 \n", "599 0 ... 0 0 0 0 \n", "\n", " miesiąc_7 miesiąc_8 miesiąc_9 miesiąc_10 miesiąc_11 miesiąc_12 \n", "0 0 0 0 0 0 0 \n", "1 0 0 0 0 0 0 \n", "2 0 0 0 0 0 0 \n", "3 0 0 0 0 0 0 \n", "4 0 0 0 0 0 0 \n", ".. ... ... ... ... ... ... \n", "595 0 1 0 0 0 0 \n", "596 0 0 1 0 0 0 \n", "597 0 0 0 1 0 0 \n", "598 0 0 0 0 1 0 \n", "599 0 0 0 0 0 1 \n", "\n", "[9360 rows x 73 columns]" ] }, "execution_count": 108, "metadata": {}, "output_type": "execute_result" } ], "source": [ "x" ] }, { "cell_type": "code", "execution_count": 109, "id": "ede98181", "metadata": {}, "outputs": [], "source": [ "y = pd.read_csv('train/expected.tsv', sep='\\t', names=['rainfall'])\n", "y2 = pd.read_csv('dev-0/expected.tsv', sep='\\t', names=['rainfall'])\n", "#y = np.array(y).reshape(1,-1)\n", "y = pd.concat([y,y2])" ] }, { "cell_type": "code", "execution_count": 110, "id": "9a950571", "metadata": {}, "outputs": [], "source": [ "# Define model\n", "model = Sequential()\n", "model.add(Dense(2048, input_dim=73, activation= \"relu\"))\n", "model.add(Dense(1024, activation= \"relu\"))\n", "model.add(Dense(512, activation= \"relu\"))\n", "model.add(Dense(256, activation= \"relu\"))\n", "model.add(Dense(128, activation= \"relu\"))\n", "model.add(Dense(64, activation= \"relu\"))\n", "model.add(Dense(32, activation= \"relu\"))\n", "model.add(Dense(16, activation= \"relu\"))\n", "model.add(Dense(1))\n", "#model.summary() #Print model Summary" ] }, { "cell_type": "code", "execution_count": 111, "id": "f68e43f9", "metadata": {}, "outputs": [], "source": [ "df['id_stacji'] = np.asarray(df['id_stacji']).astype('float32')\n", "df['rok'] = np.asarray(df['rok']).astype('float32')\n", "df['miesiąc'] = np.asarray(df['miesiąc']).astype('float32')" ] }, { "cell_type": "code", "execution_count": 112, "id": "c1036c04", "metadata": {}, "outputs": [], "source": [ "y = np.asarray(y).astype('float32')" ] }, { "cell_type": "code", "execution_count": 113, "id": "cec44474", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(None, 73) \n", "(None, 1) \n", "dense_44 (None, 73) float32\n", "dense_45 (None, 2048) float32\n", "dense_46 (None, 1024) float32\n", "dense_47 (None, 512) float32\n", "dense_48 (None, 256) float32\n", "dense_49 (None, 128) float32\n", "dense_50 (None, 64) float32\n", "dense_51 (None, 32) float32\n", "dense_52 (None, 16) float32\n" ] }, { "data": { "text/plain": [ "[None, None, None, None, None, None, None, None, None]" ] }, "execution_count": 113, "metadata": {}, "output_type": "execute_result" } ], "source": [ "[print(i.shape, i.dtype) for i in model.inputs]\n", "[print(o.shape, o.dtype) for o in model.outputs]\n", "[print(l.name, l.input_shape, l.dtype) for l in model.layers]" ] }, { "cell_type": "code", "execution_count": 114, "id": "eb9cb318", "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Epoch 1/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 1108.6758 - mean_squared_error: 1108.6758\n", "Epoch 2/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 671.0632 - mean_squared_error: 671.0632\n", "Epoch 3/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 536.2025 - mean_squared_error: 536.2025\n", "Epoch 4/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 457.3617 - mean_squared_error: 457.3617\n", "Epoch 5/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 406.1862 - mean_squared_error: 406.1862\n", "Epoch 6/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 369.4316 - mean_squared_error: 369.4316\n", "Epoch 7/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 312.5139 - mean_squared_error: 312.5139\n", "Epoch 8/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 270.2833 - mean_squared_error: 270.2833\n", "Epoch 9/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 223.4037 - mean_squared_error: 223.4037\n", "Epoch 10/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 179.4202 - mean_squared_error: 179.4202\n", "Epoch 11/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 143.8777 - mean_squared_error: 143.8777\n", "Epoch 12/80\n", "293/293 [==============================] - 5s 18ms/step - loss: 135.4522 - mean_squared_error: 135.4522\n", "Epoch 13/80\n", "293/293 [==============================] - 5s 18ms/step - loss: 109.2838 - mean_squared_error: 109.2838\n", "Epoch 14/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 88.6090 - mean_squared_error: 88.6090\n", "Epoch 15/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 69.3139 - mean_squared_error: 69.3139\n", "Epoch 16/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 67.1195 - mean_squared_error: 67.1195\n", "Epoch 17/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 59.6054 - mean_squared_error: 59.6054\n", "Epoch 18/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 50.4958 - mean_squared_error: 50.4958\n", "Epoch 19/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 41.2413 - mean_squared_error: 41.2413\n", "Epoch 20/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 35.0757 - mean_squared_error: 35.0757\n", "Epoch 21/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 43.3807 - mean_squared_error: 43.3807\n", "Epoch 22/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 48.1348 - mean_squared_error: 48.1348\n", "Epoch 23/80\n", "293/293 [==============================] - 5s 18ms/step - loss: 52.9108 - mean_squared_error: 52.9108\n", "Epoch 24/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 40.8023 - mean_squared_error: 40.8023\n", "Epoch 25/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 35.4987 - mean_squared_error: 35.4987\n", "Epoch 26/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 35.0609 - mean_squared_error: 35.0609\n", "Epoch 27/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 39.9937 - mean_squared_error: 39.9937\n", "Epoch 28/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 29.5927 - mean_squared_error: 29.5927\n", "Epoch 29/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 33.4916 - mean_squared_error: 33.4916\n", "Epoch 30/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 37.4889 - mean_squared_error: 37.4889\n", "Epoch 31/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 36.7416 - mean_squared_error: 36.7416\n", "Epoch 32/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 34.1706 - mean_squared_error: 34.1706\n", "Epoch 33/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 29.5588 - mean_squared_error: 29.5588\n", "Epoch 34/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 35.8357 - mean_squared_error: 35.8357\n", "Epoch 35/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 33.4907 - mean_squared_error: 33.4907\n", "Epoch 36/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 26.6265 - mean_squared_error: 26.6265\n", "Epoch 37/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 23.5669 - mean_squared_error: 23.5669\n", "Epoch 38/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 20.1027 - mean_squared_error: 20.1027\n", "Epoch 39/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 19.0630 - mean_squared_error: 19.0630\n", "Epoch 40/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 22.2653 - mean_squared_error: 22.2653\n", "Epoch 41/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 28.3499 - mean_squared_error: 28.3499\n", "Epoch 42/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 30.2943 - mean_squared_error: 30.2943\n", "Epoch 43/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 30.8464 - mean_squared_error: 30.8464\n", "Epoch 44/80\n", "293/293 [==============================] - 5s 18ms/step - loss: 25.8581 - mean_squared_error: 25.8581\n", "Epoch 45/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 22.0973 - mean_squared_error: 22.0973\n", "Epoch 46/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 20.3286 - mean_squared_error: 20.3286\n", "Epoch 47/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 20.7386 - mean_squared_error: 20.7386\n", "Epoch 48/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 20.1520 - mean_squared_error: 20.1520\n", "Epoch 49/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 21.0666 - mean_squared_error: 21.0666\n", "Epoch 50/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 20.2202 - mean_squared_error: 20.2202\n", "Epoch 51/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 20.7954 - mean_squared_error: 20.7954\n", "Epoch 52/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 16.0701 - mean_squared_error: 16.0701\n", "Epoch 53/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 16.0172 - mean_squared_error: 16.0172\n", "Epoch 54/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 16.2924 - mean_squared_error: 16.2924\n", "Epoch 55/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 16.6287 - mean_squared_error: 16.6287\n", "Epoch 56/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 16.3168 - mean_squared_error: 16.3168\n", "Epoch 57/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 18.8847 - mean_squared_error: 18.8847\n", "Epoch 58/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 20.1943 - mean_squared_error: 20.1943\n", "Epoch 59/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 22.6101 - mean_squared_error: 22.6101\n", "Epoch 60/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 19.8736 - mean_squared_error: 19.8736\n", "Epoch 61/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 19.8947 - mean_squared_error: 19.8947\n", "Epoch 62/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 19.0540 - mean_squared_error: 19.0540\n", "Epoch 63/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 18.1842 - mean_squared_error: 18.1842\n", "Epoch 64/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 15.4725 - mean_squared_error: 15.4725\n", "Epoch 65/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 16.2298 - mean_squared_error: 16.2298\n", "Epoch 66/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 13.2303 - mean_squared_error: 13.2303\n", "Epoch 67/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 14.2212 - mean_squared_error: 14.2212\n", "Epoch 68/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 12.7895 - mean_squared_error: 12.7895\n", "Epoch 69/80\n", "293/293 [==============================] - 5s 18ms/step - loss: 15.7551 - mean_squared_error: 15.7551\n", "Epoch 70/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 18.4030 - mean_squared_error: 18.4030\n", "Epoch 71/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 16.0214 - mean_squared_error: 16.0214\n", "Epoch 72/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 12.3694 - mean_squared_error: 12.3694\n", "Epoch 73/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 10.5107 - mean_squared_error: 10.5107\n", "Epoch 74/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 11.7746 - mean_squared_error: 11.7746\n", "Epoch 75/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 11.6589 - mean_squared_error: 11.6589\n", "Epoch 76/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 14.1691 - mean_squared_error: 14.1691\n", "Epoch 77/80\n", "293/293 [==============================] - 5s 16ms/step - loss: 15.9365 - mean_squared_error: 15.9365\n", "Epoch 78/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 15.4616 - mean_squared_error: 15.4616\n", "Epoch 79/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 13.2958 - mean_squared_error: 13.2958\n", "Epoch 80/80\n", "293/293 [==============================] - 5s 17ms/step - loss: 11.3826 - mean_squared_error: 11.3826\n" ] }, { "data": { "text/plain": [ "" ] }, "execution_count": 114, "metadata": {}, "output_type": "execute_result" } ], "source": [ "model.compile(loss= \"mean_squared_error\" , optimizer=\"adam\", metrics=[\"mean_squared_error\"])\n", "model.fit(x, y, epochs=80)" ] }, { "cell_type": "code", "execution_count": 115, "id": "bad4d35a", "metadata": {}, "outputs": [], "source": [ "x_test = pd.read_csv('test-A/in.tsv', sep='\\t', names=in_columns)\n", "#y_test = pd.read_csv('test-A/expected.tsv', sep='\\t',names=['rainfall'])\n", "#x_test = x_test.drop(['nazwa_stacji', 'typ_zbioru'],axis=1)\n", "#df_train = pd.read_csv('train/in.tsv', names=in_columns, sep='\\t')\n", "df_train = pd.read_csv('train/in.tsv', names=in_columns, sep='\\t')\n", "df2_train = pd.read_csv('dev-0/in.tsv', names=in_columns, sep='\\t')\n", "df_train = pd.concat([df_train, df2_train])" ] }, { "cell_type": "code", "execution_count": 116, "id": "a3b6fff0", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "10080" ] }, "execution_count": 116, "metadata": {}, "output_type": "execute_result" } ], "source": [ "x_test = pd.concat([x_test,df_train])\n", "len(x_test)" ] }, { "cell_type": "code", "execution_count": 117, "id": "cdf89362", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "10080" ] }, "execution_count": 117, "metadata": {}, "output_type": "execute_result" } ], "source": [ "x_test = x_test.drop(['nazwa_stacji', 'typ_zbioru'],axis=1)\n", "len(x_test)" ] }, { "cell_type": "code", "execution_count": 118, "id": "fe00b876", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
id_stacji_249180010id_stacji_249190560id_stacji_249200370id_stacji_249200490id_stacji_249220150id_stacji_249220180id_stacji_250190160id_stacji_250190390id_stacji_250210130id_stacji_251170090...miesiąc_3miesiąc_4miesiąc_5miesiąc_6miesiąc_7miesiąc_8miesiąc_9miesiąc_10miesiąc_11miesiąc_12
00010000000...0000000000
10010000000...0000000000
20010000000...1000000000
30010000000...0100000000
40010000000...0010000000
..................................................................
5950000000000...0000010000
5960000000000...0000001000
5970000000000...0000000100
5980000000000...0000000010
5990000000000...0000000001
\n", "

10080 rows × 73 columns

\n", "
" ], "text/plain": [ " id_stacji_249180010 id_stacji_249190560 id_stacji_249200370 \\\n", "0 0 0 1 \n", "1 0 0 1 \n", "2 0 0 1 \n", "3 0 0 1 \n", "4 0 0 1 \n", ".. ... ... ... \n", "595 0 0 0 \n", "596 0 0 0 \n", "597 0 0 0 \n", "598 0 0 0 \n", "599 0 0 0 \n", "\n", " id_stacji_249200490 id_stacji_249220150 id_stacji_249220180 \\\n", "0 0 0 0 \n", "1 0 0 0 \n", "2 0 0 0 \n", "3 0 0 0 \n", "4 0 0 0 \n", ".. ... ... ... \n", "595 0 0 0 \n", "596 0 0 0 \n", "597 0 0 0 \n", "598 0 0 0 \n", "599 0 0 0 \n", "\n", " id_stacji_250190160 id_stacji_250190390 id_stacji_250210130 \\\n", "0 0 0 0 \n", "1 0 0 0 \n", "2 0 0 0 \n", "3 0 0 0 \n", "4 0 0 0 \n", ".. ... ... ... \n", "595 0 0 0 \n", "596 0 0 0 \n", "597 0 0 0 \n", "598 0 0 0 \n", "599 0 0 0 \n", "\n", " id_stacji_251170090 ... miesiąc_3 miesiąc_4 miesiąc_5 miesiąc_6 \\\n", "0 0 ... 0 0 0 0 \n", "1 0 ... 0 0 0 0 \n", "2 0 ... 1 0 0 0 \n", "3 0 ... 0 1 0 0 \n", "4 0 ... 0 0 1 0 \n", ".. ... ... ... ... ... ... \n", "595 0 ... 0 0 0 0 \n", "596 0 ... 0 0 0 0 \n", "597 0 ... 0 0 0 0 \n", "598 0 ... 0 0 0 0 \n", "599 0 ... 0 0 0 0 \n", "\n", " miesiąc_7 miesiąc_8 miesiąc_9 miesiąc_10 miesiąc_11 miesiąc_12 \n", "0 0 0 0 0 0 0 \n", "1 0 0 0 0 0 0 \n", "2 0 0 0 0 0 0 \n", "3 0 0 0 0 0 0 \n", "4 0 0 0 0 0 0 \n", ".. ... ... ... ... ... ... \n", "595 0 1 0 0 0 0 \n", "596 0 0 1 0 0 0 \n", "597 0 0 0 1 0 0 \n", "598 0 0 0 0 1 0 \n", "599 0 0 0 0 0 1 \n", "\n", "[10080 rows x 73 columns]" ] }, "execution_count": 118, "metadata": {}, "output_type": "execute_result" } ], "source": [ "x_test = pd.get_dummies(x_test,columns = ['id_stacji','rok','miesiąc'])\n", "x_test" ] }, { "cell_type": "code", "execution_count": 119, "id": "657a7976", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
id_stacji_249180010id_stacji_249190560id_stacji_249200370id_stacji_249200490id_stacji_249220150id_stacji_249220180id_stacji_250190160id_stacji_250190390id_stacji_250210130id_stacji_251170090...miesiąc_3miesiąc_4miesiąc_5miesiąc_6miesiąc_7miesiąc_8miesiąc_9miesiąc_10miesiąc_11miesiąc_12
00010000000...0000000000
10010000000...0000000000
20010000000...1000000000
30010000000...0100000000
40010000000...0010000000
..................................................................
7150000000000...0000010000
7160000000000...0000001000
7170000000000...0000000100
7180000000000...0000000010
7190000000000...0000000001
\n", "

720 rows × 73 columns

\n", "
" ], "text/plain": [ " id_stacji_249180010 id_stacji_249190560 id_stacji_249200370 \\\n", "0 0 0 1 \n", "1 0 0 1 \n", "2 0 0 1 \n", "3 0 0 1 \n", "4 0 0 1 \n", ".. ... ... ... \n", "715 0 0 0 \n", "716 0 0 0 \n", "717 0 0 0 \n", "718 0 0 0 \n", "719 0 0 0 \n", "\n", " id_stacji_249200490 id_stacji_249220150 id_stacji_249220180 \\\n", "0 0 0 0 \n", "1 0 0 0 \n", "2 0 0 0 \n", "3 0 0 0 \n", "4 0 0 0 \n", ".. ... ... ... \n", "715 0 0 0 \n", "716 0 0 0 \n", "717 0 0 0 \n", "718 0 0 0 \n", "719 0 0 0 \n", "\n", " id_stacji_250190160 id_stacji_250190390 id_stacji_250210130 \\\n", "0 0 0 0 \n", "1 0 0 0 \n", "2 0 0 0 \n", "3 0 0 0 \n", "4 0 0 0 \n", ".. ... ... ... \n", "715 0 0 0 \n", "716 0 0 0 \n", "717 0 0 0 \n", "718 0 0 0 \n", "719 0 0 0 \n", "\n", " id_stacji_251170090 ... miesiąc_3 miesiąc_4 miesiąc_5 miesiąc_6 \\\n", "0 0 ... 0 0 0 0 \n", "1 0 ... 0 0 0 0 \n", "2 0 ... 1 0 0 0 \n", "3 0 ... 0 1 0 0 \n", "4 0 ... 0 0 1 0 \n", ".. ... ... ... ... ... ... \n", "715 0 ... 0 0 0 0 \n", "716 0 ... 0 0 0 0 \n", "717 0 ... 0 0 0 0 \n", "718 0 ... 0 0 0 0 \n", "719 0 ... 0 0 0 0 \n", "\n", " miesiąc_7 miesiąc_8 miesiąc_9 miesiąc_10 miesiąc_11 miesiąc_12 \n", "0 0 0 0 0 0 0 \n", "1 0 0 0 0 0 0 \n", "2 0 0 0 0 0 0 \n", "3 0 0 0 0 0 0 \n", "4 0 0 0 0 0 0 \n", ".. ... ... ... ... ... ... \n", "715 0 1 0 0 0 0 \n", "716 0 0 1 0 0 0 \n", "717 0 0 0 1 0 0 \n", "718 0 0 0 0 1 0 \n", "719 0 0 0 0 0 1 \n", "\n", "[720 rows x 73 columns]" ] }, "execution_count": 119, "metadata": {}, "output_type": "execute_result" } ], "source": [ "x_test = x_test.iloc[:-9360]\n", "x_test" ] }, { "cell_type": "code", "execution_count": 120, "id": "1163c550", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "23/23 [==============================] - 0s 4ms/step\n" ] } ], "source": [ "pred= model.predict(x_test)" ] }, { "cell_type": "code", "execution_count": 121, "id": "6c24ee76", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "23/23 [==============================] - 0s 4ms/step\n" ] } ], "source": [ "pred= model.predict(x_test)\n", "out = pd.DataFrame(pred)\n", "out.to_csv('test-A/out.tsv',sep='\\t',header=False, index=False)" ] } ], "metadata": { "interpreter": { "hash": "754a2b6bedec8aae7cfc361a819067f3f72b778cb88f366be5c7fdc236f21674" }, "kernelspec": { "display_name": "Python 3.9.7 ('base')", "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": "3.9.7" } }, "nbformat": 4, "nbformat_minor": 5 }