precipitation-pl/solution.ipynb
2022-05-23 15:41:22 +02:00

2122 lines
76 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"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": [
"<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>id_stacji_249180010</th>\n",
" <th>id_stacji_249190560</th>\n",
" <th>id_stacji_249200370</th>\n",
" <th>id_stacji_249200490</th>\n",
" <th>id_stacji_249220150</th>\n",
" <th>id_stacji_249220180</th>\n",
" <th>id_stacji_250190160</th>\n",
" <th>id_stacji_250190390</th>\n",
" <th>id_stacji_250210130</th>\n",
" <th>id_stacji_251170090</th>\n",
" <th>...</th>\n",
" <th>miesiąc_3</th>\n",
" <th>miesiąc_4</th>\n",
" <th>miesiąc_5</th>\n",
" <th>miesiąc_6</th>\n",
" <th>miesiąc_7</th>\n",
" <th>miesiąc_8</th>\n",
" <th>miesiąc_9</th>\n",
" <th>miesiąc_10</th>\n",
" <th>miesiąc_11</th>\n",
" <th>miesiąc_12</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>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",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>715</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>716</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>717</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>718</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>719</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>10080 rows × 73 columns</p>\n",
"</div>"
],
"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": [
"<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>id_stacji_249180010</th>\n",
" <th>id_stacji_249190560</th>\n",
" <th>id_stacji_249200370</th>\n",
" <th>id_stacji_249200490</th>\n",
" <th>id_stacji_249220150</th>\n",
" <th>id_stacji_249220180</th>\n",
" <th>id_stacji_250190160</th>\n",
" <th>id_stacji_250190390</th>\n",
" <th>id_stacji_250210130</th>\n",
" <th>id_stacji_251170090</th>\n",
" <th>...</th>\n",
" <th>miesiąc_3</th>\n",
" <th>miesiąc_4</th>\n",
" <th>miesiąc_5</th>\n",
" <th>miesiąc_6</th>\n",
" <th>miesiąc_7</th>\n",
" <th>miesiąc_8</th>\n",
" <th>miesiąc_9</th>\n",
" <th>miesiąc_10</th>\n",
" <th>miesiąc_11</th>\n",
" <th>miesiąc_12</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>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",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>595</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>596</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>597</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>598</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>599</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>9360 rows × 73 columns</p>\n",
"</div>"
],
"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) <dtype: 'float32'>\n",
"(None, 1) <dtype: 'float32'>\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": [
"<keras.callbacks.History at 0x1b61bab69d0>"
]
},
"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": [
"<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>id_stacji_249180010</th>\n",
" <th>id_stacji_249190560</th>\n",
" <th>id_stacji_249200370</th>\n",
" <th>id_stacji_249200490</th>\n",
" <th>id_stacji_249220150</th>\n",
" <th>id_stacji_249220180</th>\n",
" <th>id_stacji_250190160</th>\n",
" <th>id_stacji_250190390</th>\n",
" <th>id_stacji_250210130</th>\n",
" <th>id_stacji_251170090</th>\n",
" <th>...</th>\n",
" <th>miesiąc_3</th>\n",
" <th>miesiąc_4</th>\n",
" <th>miesiąc_5</th>\n",
" <th>miesiąc_6</th>\n",
" <th>miesiąc_7</th>\n",
" <th>miesiąc_8</th>\n",
" <th>miesiąc_9</th>\n",
" <th>miesiąc_10</th>\n",
" <th>miesiąc_11</th>\n",
" <th>miesiąc_12</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>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",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>595</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>596</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>597</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>598</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>599</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>10080 rows × 73 columns</p>\n",
"</div>"
],
"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": [
"<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>id_stacji_249180010</th>\n",
" <th>id_stacji_249190560</th>\n",
" <th>id_stacji_249200370</th>\n",
" <th>id_stacji_249200490</th>\n",
" <th>id_stacji_249220150</th>\n",
" <th>id_stacji_249220180</th>\n",
" <th>id_stacji_250190160</th>\n",
" <th>id_stacji_250190390</th>\n",
" <th>id_stacji_250210130</th>\n",
" <th>id_stacji_251170090</th>\n",
" <th>...</th>\n",
" <th>miesiąc_3</th>\n",
" <th>miesiąc_4</th>\n",
" <th>miesiąc_5</th>\n",
" <th>miesiąc_6</th>\n",
" <th>miesiąc_7</th>\n",
" <th>miesiąc_8</th>\n",
" <th>miesiąc_9</th>\n",
" <th>miesiąc_10</th>\n",
" <th>miesiąc_11</th>\n",
" <th>miesiąc_12</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>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",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>715</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>716</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>717</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>718</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>719</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>720 rows × 73 columns</p>\n",
"</div>"
],
"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
}