|
|
@@ -9,7 +9,7 @@
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "code",
|
|
|
- "execution_count": 7,
|
|
|
+ "execution_count": 1,
|
|
|
"metadata": {},
|
|
|
"outputs": [],
|
|
|
"source": [
|
|
|
@@ -21,7 +21,7 @@
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "code",
|
|
|
- "execution_count": 8,
|
|
|
+ "execution_count": 2,
|
|
|
"metadata": {},
|
|
|
"outputs": [
|
|
|
{
|
|
|
@@ -30,7 +30,7 @@
|
|
|
"40"
|
|
|
]
|
|
|
},
|
|
|
- "execution_count": 8,
|
|
|
+ "execution_count": 2,
|
|
|
"metadata": {},
|
|
|
"output_type": "execute_result"
|
|
|
}
|
|
|
@@ -42,94 +42,20 @@
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "code",
|
|
|
- "execution_count": 10,
|
|
|
+ "execution_count": 3,
|
|
|
"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>temperature</th>\n",
|
|
|
- " <th>energy</th>\n",
|
|
|
- " </tr>\n",
|
|
|
- " <tr>\n",
|
|
|
- " <th>timestamp</th>\n",
|
|
|
- " <th></th>\n",
|
|
|
- " <th></th>\n",
|
|
|
- " </tr>\n",
|
|
|
- " </thead>\n",
|
|
|
- " <tbody>\n",
|
|
|
- " <tr>\n",
|
|
|
- " <th>2016-09-18 04:00:00</th>\n",
|
|
|
- " <td>56.240300</td>\n",
|
|
|
- " <td>1.682686</td>\n",
|
|
|
- " </tr>\n",
|
|
|
- " <tr>\n",
|
|
|
- " <th>2016-09-18 04:15:00</th>\n",
|
|
|
- " <td>56.087501</td>\n",
|
|
|
- " <td>2.086212</td>\n",
|
|
|
- " </tr>\n",
|
|
|
- " <tr>\n",
|
|
|
- " <th>2016-09-18 04:30:00</th>\n",
|
|
|
- " <td>56.213232</td>\n",
|
|
|
- " <td>1.687880</td>\n",
|
|
|
- " </tr>\n",
|
|
|
- " <tr>\n",
|
|
|
- " <th>2016-09-18 04:45:00</th>\n",
|
|
|
- " <td>56.400049</td>\n",
|
|
|
- " <td>1.926518</td>\n",
|
|
|
- " </tr>\n",
|
|
|
- " <tr>\n",
|
|
|
- " <th>2016-09-18 05:00:00</th>\n",
|
|
|
- " <td>56.592497</td>\n",
|
|
|
- " <td>1.922459</td>\n",
|
|
|
- " </tr>\n",
|
|
|
- " </tbody>\n",
|
|
|
- "</table>\n",
|
|
|
- "</div>"
|
|
|
- ],
|
|
|
- "text/plain": [
|
|
|
- " temperature energy\n",
|
|
|
- "timestamp \n",
|
|
|
- "2016-09-18 04:00:00 56.240300 1.682686\n",
|
|
|
- "2016-09-18 04:15:00 56.087501 2.086212\n",
|
|
|
- "2016-09-18 04:30:00 56.213232 1.687880\n",
|
|
|
- "2016-09-18 04:45:00 56.400049 1.926518\n",
|
|
|
- "2016-09-18 05:00:00 56.592497 1.922459"
|
|
|
- ]
|
|
|
- },
|
|
|
- "execution_count": 10,
|
|
|
- "metadata": {},
|
|
|
- "output_type": "execute_result"
|
|
|
- },
|
|
|
- {
|
|
|
"name": "stdout",
|
|
|
"output_type": "stream",
|
|
|
"text": [
|
|
|
"<class 'pandas.core.frame.DataFrame'>\n",
|
|
|
- "DatetimeIndex: 36960 entries, 2016-09-18 04:00:00 to 2017-10-08 03:45:00\n",
|
|
|
+ "DatetimeIndex: 100786 entries, 2014-01-01 06:15:00 to 2016-11-16 02:30:00\n",
|
|
|
"Data columns (total 2 columns):\n",
|
|
|
- "temperature 36960 non-null float64\n",
|
|
|
- "energy 36960 non-null float64\n",
|
|
|
+ "temperature 100786 non-null float64\n",
|
|
|
+ "energy 100786 non-null float64\n",
|
|
|
"dtypes: float64(2)\n",
|
|
|
- "memory usage: 866.2 KB\n"
|
|
|
+ "memory usage: 2.3 MB\n"
|
|
|
]
|
|
|
}
|
|
|
],
|
|
|
@@ -141,7 +67,7 @@
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "code",
|
|
|
- "execution_count": 15,
|
|
|
+ "execution_count": 6,
|
|
|
"metadata": {},
|
|
|
"outputs": [],
|
|
|
"source": [
|
|
|
@@ -173,7 +99,7 @@
|
|
|
" X[\"sin_time_of_day\"], X[\"cos_time_of_day\"] = _cyclical_encoding(\n",
|
|
|
" X[\"time_of_day\"], period=24\n",
|
|
|
" )\n",
|
|
|
- " X[\"sin_day_of_year\"], X[\"cos_day_of_year\"] = _cylical_encoding(\n",
|
|
|
+ " X[\"sin_day_of_year\"], X[\"cos_day_of_year\"] = _cyclical_encoding(\n",
|
|
|
" X[\"day_of_year\"], period=366\n",
|
|
|
" )\n",
|
|
|
" return X\n",
|
|
|
@@ -186,7 +112,7 @@
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "code",
|
|
|
- "execution_count": 16,
|
|
|
+ "execution_count": 7,
|
|
|
"metadata": {},
|
|
|
"outputs": [
|
|
|
{
|
|
|
@@ -233,91 +159,91 @@
|
|
|
" </thead>\n",
|
|
|
" <tbody>\n",
|
|
|
" <tr>\n",
|
|
|
- " <th>2016-09-18 04:00:00</th>\n",
|
|
|
- " <td>56.240300</td>\n",
|
|
|
- " <td>1.682686</td>\n",
|
|
|
- " <td>4.00</td>\n",
|
|
|
- " <td>262</td>\n",
|
|
|
- " <td>0.866025</td>\n",
|
|
|
- " <td>0.500000</td>\n",
|
|
|
- " <td>-0.977064</td>\n",
|
|
|
- " <td>-0.212947</td>\n",
|
|
|
+ " <th>2014-01-01 06:15:00</th>\n",
|
|
|
+ " <td>40.987233</td>\n",
|
|
|
+ " <td>43.012862</td>\n",
|
|
|
+ " <td>6.25</td>\n",
|
|
|
+ " <td>1</td>\n",
|
|
|
+ " <td>0.997859</td>\n",
|
|
|
+ " <td>-0.065403</td>\n",
|
|
|
+ " <td>0.017166</td>\n",
|
|
|
+ " <td>0.999853</td>\n",
|
|
|
" </tr>\n",
|
|
|
" <tr>\n",
|
|
|
- " <th>2016-09-18 04:15:00</th>\n",
|
|
|
- " <td>56.087501</td>\n",
|
|
|
- " <td>2.086212</td>\n",
|
|
|
- " <td>4.25</td>\n",
|
|
|
- " <td>262</td>\n",
|
|
|
- " <td>0.896873</td>\n",
|
|
|
- " <td>0.442289</td>\n",
|
|
|
- " <td>-0.977064</td>\n",
|
|
|
- " <td>-0.212947</td>\n",
|
|
|
+ " <th>2014-01-01 06:30:00</th>\n",
|
|
|
+ " <td>41.007768</td>\n",
|
|
|
+ " <td>43.780204</td>\n",
|
|
|
+ " <td>6.50</td>\n",
|
|
|
+ " <td>1</td>\n",
|
|
|
+ " <td>0.991445</td>\n",
|
|
|
+ " <td>-0.130526</td>\n",
|
|
|
+ " <td>0.017166</td>\n",
|
|
|
+ " <td>0.999853</td>\n",
|
|
|
" </tr>\n",
|
|
|
" <tr>\n",
|
|
|
- " <th>2016-09-18 04:30:00</th>\n",
|
|
|
- " <td>56.213232</td>\n",
|
|
|
- " <td>1.687880</td>\n",
|
|
|
- " <td>4.50</td>\n",
|
|
|
- " <td>262</td>\n",
|
|
|
- " <td>0.923880</td>\n",
|
|
|
- " <td>0.382683</td>\n",
|
|
|
- " <td>-0.977064</td>\n",
|
|
|
- " <td>-0.212947</td>\n",
|
|
|
+ " <th>2014-01-01 06:45:00</th>\n",
|
|
|
+ " <td>41.002971</td>\n",
|
|
|
+ " <td>43.012709</td>\n",
|
|
|
+ " <td>6.75</td>\n",
|
|
|
+ " <td>1</td>\n",
|
|
|
+ " <td>0.980785</td>\n",
|
|
|
+ " <td>-0.195090</td>\n",
|
|
|
+ " <td>0.017166</td>\n",
|
|
|
+ " <td>0.999853</td>\n",
|
|
|
" </tr>\n",
|
|
|
" <tr>\n",
|
|
|
- " <th>2016-09-18 04:45:00</th>\n",
|
|
|
- " <td>56.400049</td>\n",
|
|
|
- " <td>1.926518</td>\n",
|
|
|
- " <td>4.75</td>\n",
|
|
|
- " <td>262</td>\n",
|
|
|
- " <td>0.946930</td>\n",
|
|
|
- " <td>0.321439</td>\n",
|
|
|
- " <td>-0.977064</td>\n",
|
|
|
- " <td>-0.212947</td>\n",
|
|
|
+ " <th>2014-01-01 07:00:00</th>\n",
|
|
|
+ " <td>41.008100</td>\n",
|
|
|
+ " <td>42.631804</td>\n",
|
|
|
+ " <td>7.00</td>\n",
|
|
|
+ " <td>1</td>\n",
|
|
|
+ " <td>0.965926</td>\n",
|
|
|
+ " <td>-0.258819</td>\n",
|
|
|
+ " <td>0.017166</td>\n",
|
|
|
+ " <td>0.999853</td>\n",
|
|
|
" </tr>\n",
|
|
|
" <tr>\n",
|
|
|
- " <th>2016-09-18 05:00:00</th>\n",
|
|
|
- " <td>56.592497</td>\n",
|
|
|
- " <td>1.922459</td>\n",
|
|
|
- " <td>5.00</td>\n",
|
|
|
- " <td>262</td>\n",
|
|
|
- " <td>0.965926</td>\n",
|
|
|
- " <td>0.258819</td>\n",
|
|
|
- " <td>-0.977064</td>\n",
|
|
|
- " <td>-0.212947</td>\n",
|
|
|
+ " <th>2014-01-01 07:15:00</th>\n",
|
|
|
+ " <td>41.005961</td>\n",
|
|
|
+ " <td>42.627307</td>\n",
|
|
|
+ " <td>7.25</td>\n",
|
|
|
+ " <td>1</td>\n",
|
|
|
+ " <td>0.946930</td>\n",
|
|
|
+ " <td>-0.321439</td>\n",
|
|
|
+ " <td>0.017166</td>\n",
|
|
|
+ " <td>0.999853</td>\n",
|
|
|
" </tr>\n",
|
|
|
" </tbody>\n",
|
|
|
"</table>\n",
|
|
|
"</div>"
|
|
|
],
|
|
|
"text/plain": [
|
|
|
- " temperature energy time_of_day day_of_year \\\n",
|
|
|
- "timestamp \n",
|
|
|
- "2016-09-18 04:00:00 56.240300 1.682686 4.00 262 \n",
|
|
|
- "2016-09-18 04:15:00 56.087501 2.086212 4.25 262 \n",
|
|
|
- "2016-09-18 04:30:00 56.213232 1.687880 4.50 262 \n",
|
|
|
- "2016-09-18 04:45:00 56.400049 1.926518 4.75 262 \n",
|
|
|
- "2016-09-18 05:00:00 56.592497 1.922459 5.00 262 \n",
|
|
|
+ " temperature energy time_of_day day_of_year \\\n",
|
|
|
+ "timestamp \n",
|
|
|
+ "2014-01-01 06:15:00 40.987233 43.012862 6.25 1 \n",
|
|
|
+ "2014-01-01 06:30:00 41.007768 43.780204 6.50 1 \n",
|
|
|
+ "2014-01-01 06:45:00 41.002971 43.012709 6.75 1 \n",
|
|
|
+ "2014-01-01 07:00:00 41.008100 42.631804 7.00 1 \n",
|
|
|
+ "2014-01-01 07:15:00 41.005961 42.627307 7.25 1 \n",
|
|
|
"\n",
|
|
|
" sin_time_of_day cos_time_of_day sin_day_of_year \\\n",
|
|
|
"timestamp \n",
|
|
|
- "2016-09-18 04:00:00 0.866025 0.500000 -0.977064 \n",
|
|
|
- "2016-09-18 04:15:00 0.896873 0.442289 -0.977064 \n",
|
|
|
- "2016-09-18 04:30:00 0.923880 0.382683 -0.977064 \n",
|
|
|
- "2016-09-18 04:45:00 0.946930 0.321439 -0.977064 \n",
|
|
|
- "2016-09-18 05:00:00 0.965926 0.258819 -0.977064 \n",
|
|
|
+ "2014-01-01 06:15:00 0.997859 -0.065403 0.017166 \n",
|
|
|
+ "2014-01-01 06:30:00 0.991445 -0.130526 0.017166 \n",
|
|
|
+ "2014-01-01 06:45:00 0.980785 -0.195090 0.017166 \n",
|
|
|
+ "2014-01-01 07:00:00 0.965926 -0.258819 0.017166 \n",
|
|
|
+ "2014-01-01 07:15:00 0.946930 -0.321439 0.017166 \n",
|
|
|
"\n",
|
|
|
" cos_day_of_year \n",
|
|
|
"timestamp \n",
|
|
|
- "2016-09-18 04:00:00 -0.212947 \n",
|
|
|
- "2016-09-18 04:15:00 -0.212947 \n",
|
|
|
- "2016-09-18 04:30:00 -0.212947 \n",
|
|
|
- "2016-09-18 04:45:00 -0.212947 \n",
|
|
|
- "2016-09-18 05:00:00 -0.212947 "
|
|
|
+ "2014-01-01 06:15:00 0.999853 \n",
|
|
|
+ "2014-01-01 06:30:00 0.999853 \n",
|
|
|
+ "2014-01-01 06:45:00 0.999853 \n",
|
|
|
+ "2014-01-01 07:00:00 0.999853 \n",
|
|
|
+ "2014-01-01 07:15:00 0.999853 "
|
|
|
]
|
|
|
},
|
|
|
- "execution_count": 16,
|
|
|
+ "execution_count": 7,
|
|
|
"metadata": {},
|
|
|
"output_type": "execute_result"
|
|
|
}
|
|
|
@@ -338,6 +264,329 @@
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "code",
|
|
|
+ "execution_count": 8,
|
|
|
+ "metadata": {},
|
|
|
+ "outputs": [],
|
|
|
+ "source": [
|
|
|
+ "class WeeklyValidator(BaseEstimator):\n",
|
|
|
+ " def __init__(self):\n",
|
|
|
+ " pass\n",
|
|
|
+ " \n",
|
|
|
+ " def fit(self, X, y):\n",
|
|
|
+ " pass\n",
|
|
|
+ " \n",
|
|
|
+ " def predict(self, X):\n",
|
|
|
+ " pass\n",
|
|
|
+ " "
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 59,
|
|
|
+ "metadata": {},
|
|
|
+ "outputs": [],
|
|
|
+ "source": [
|
|
|
+ "def run_weekly_validation(models, data):\n",
|
|
|
+ " \n",
|
|
|
+ " all_predictions = []\n",
|
|
|
+ " \n",
|
|
|
+ " feature_sets = [['time_of_day', 'day_of_year', 'temperature'], \n",
|
|
|
+ " ['sin_time_of_day', 'cos_time_of_day', 'sin_day_of_year', 'cos_day_of_year', 'temperature']]\n",
|
|
|
+ " # Iterate through features\n",
|
|
|
+ " for feature_set in feature_sets:\n",
|
|
|
+ " features='standard' if 'sin_time_of_day' not in feature_set else 'cyclical'\n",
|
|
|
+ " print(f'Using features: {features}')\n",
|
|
|
+ " # Subset to data\n",
|
|
|
+ " X = data[feature_set + ['energy']].copy()\n",
|
|
|
+ " \n",
|
|
|
+ " # Iterate through models\n",
|
|
|
+ " for model in models:\n",
|
|
|
+ " model_name = model.__class__.__name__\n",
|
|
|
+ " print(f'Using model: {model_name}')\n",
|
|
|
+ " \n",
|
|
|
+ " # Iterate through weeks in the dataset\n",
|
|
|
+ " # Must group by string formatted week and year\n",
|
|
|
+ " for (week, year), X_test in tqdm.tqdm(X.groupby([X.index.strftime('%U'), X.index.strftime('%Y')]), desc='Weeks'):\n",
|
|
|
+ " \n",
|
|
|
+ " # Subset to training data\n",
|
|
|
+ " X_train = X[X.index < X_test.index.min()].copy()\n",
|
|
|
+ " \n",
|
|
|
+ " # Can not train or test on zero observations\n",
|
|
|
+ " if len(X_train) == 0 or len(X_test) == 0:\n",
|
|
|
+ " continue\n",
|
|
|
+ " \n",
|
|
|
+ " # Targets\n",
|
|
|
+ " y_train = X_train.pop('energy')\n",
|
|
|
+ " y_test = X_test.pop('energy')\n",
|
|
|
+ " \n",
|
|
|
+ " model.fit(X_train, y_train)\n",
|
|
|
+ " predictions = model.predict(X_test)\n",
|
|
|
+ " \n",
|
|
|
+ " # Record predictions along with actual values, model, and feature set in a dataframe\n",
|
|
|
+ " predictions = pd.DataFrame(dict(predicted=predictions,\n",
|
|
|
+ " actual=y_test, \n",
|
|
|
+ " model=model_name, \n",
|
|
|
+ " features=features),\n",
|
|
|
+ " index=X_test.index)\n",
|
|
|
+ " \n",
|
|
|
+ " all_predictions.append(predictions)\n",
|
|
|
+ " # Return list of dataframes\n",
|
|
|
+ " return all_predictions"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 48,
|
|
|
+ "metadata": {},
|
|
|
+ "outputs": [],
|
|
|
+ "source": [
|
|
|
+ "import tqdm\n",
|
|
|
+ "import black"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 60,
|
|
|
+ "metadata": {},
|
|
|
+ "outputs": [],
|
|
|
+ "source": [
|
|
|
+ "from sklearn.linear_model import LinearRegression\n",
|
|
|
+ "from sklearn.ensemble import RandomForestRegressor\n",
|
|
|
+ "\n",
|
|
|
+ "# Create linear model and random forest model for regression\n",
|
|
|
+ "models = [LinearRegression(n_jobs=-1), RandomForestRegressor(n_estimators=100, max_depth=None, n_jobs=-1, random_state=100)]\n",
|
|
|
+ "# validation = run_weekly_validation(models, data)"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": null,
|
|
|
+ "metadata": {},
|
|
|
+ "outputs": [
|
|
|
+ {
|
|
|
+ "name": "stderr",
|
|
|
+ "output_type": "stream",
|
|
|
+ "text": [
|
|
|
+ "\n",
|
|
|
+ "\n",
|
|
|
+ "\n",
|
|
|
+ "\n",
|
|
|
+ "\n",
|
|
|
+ "\n",
|
|
|
+ "\n",
|
|
|
+ "Buildings: 0%| | 0/40 [00:00<?, ?it/s]"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "name": "stdout",
|
|
|
+ "output_type": "stream",
|
|
|
+ "text": [
|
|
|
+ "Using features: standard\n",
|
|
|
+ "Using model: LinearRegression\n"
|
|
|
+ ]
|
|
|
+ }
|
|
|
+ ],
|
|
|
+ "source": [
|
|
|
+ "def run_all_buildings(building_data_files):\n",
|
|
|
+ " # Run validation for all buildings\n",
|
|
|
+ " for building_file_name in tqdm.tqdm(building_data_files, desc='Buildings'):\n",
|
|
|
+ " building_data = pd.read_csv(building_file_name, parse_dates=['timestamp']).set_index('timestamp')\n",
|
|
|
+ " # Create sets of features\n",
|
|
|
+ " building_data = transforms.transform(building_data)\n",
|
|
|
+ " \n",
|
|
|
+ " # Run the validation and save the results\n",
|
|
|
+ " building_validation = run_weekly_validation(models, building_data)\n",
|
|
|
+ " # Convert from list of dataframes to single dataframe\n",
|
|
|
+ " building_validation = pd.concat(building_validation).reset_index().sort_values(['model', 'features', 'timestamp']).set_index('timestamp')\n",
|
|
|
+ " # Save off results for analysis\n",
|
|
|
+ " building_validation.to_csv(f\"{building_file_name.replace('energy_data', 'validation_results').replace('data', 'validation_results')}\")\n",
|
|
|
+ " \n",
|
|
|
+ "run_all_buildings(building_data_files)"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 41,
|
|
|
+ "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>predicted</th>\n",
|
|
|
+ " <th>actual</th>\n",
|
|
|
+ " <th>model</th>\n",
|
|
|
+ " <th>features</th>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " <tr>\n",
|
|
|
+ " <th>timestamp</th>\n",
|
|
|
+ " <th></th>\n",
|
|
|
+ " <th></th>\n",
|
|
|
+ " <th></th>\n",
|
|
|
+ " <th></th>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " </thead>\n",
|
|
|
+ " <tbody>\n",
|
|
|
+ " <tr>\n",
|
|
|
+ " <th>2016-01-02 22:45:00</th>\n",
|
|
|
+ " <td>135.545103</td>\n",
|
|
|
+ " <td>71.810619</td>\n",
|
|
|
+ " <td>RandomForestRegressor</td>\n",
|
|
|
+ " <td>cyclical</td>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " <tr>\n",
|
|
|
+ " <th>2016-01-02 23:00:00</th>\n",
|
|
|
+ " <td>144.112047</td>\n",
|
|
|
+ " <td>96.005072</td>\n",
|
|
|
+ " <td>RandomForestRegressor</td>\n",
|
|
|
+ " <td>cyclical</td>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " <tr>\n",
|
|
|
+ " <th>2016-01-02 23:15:00</th>\n",
|
|
|
+ " <td>144.322802</td>\n",
|
|
|
+ " <td>93.704430</td>\n",
|
|
|
+ " <td>RandomForestRegressor</td>\n",
|
|
|
+ " <td>cyclical</td>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " <tr>\n",
|
|
|
+ " <th>2016-01-02 23:30:00</th>\n",
|
|
|
+ " <td>143.739093</td>\n",
|
|
|
+ " <td>94.853490</td>\n",
|
|
|
+ " <td>RandomForestRegressor</td>\n",
|
|
|
+ " <td>cyclical</td>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " <tr>\n",
|
|
|
+ " <th>2016-01-02 23:45:00</th>\n",
|
|
|
+ " <td>140.805196</td>\n",
|
|
|
+ " <td>92.931160</td>\n",
|
|
|
+ " <td>RandomForestRegressor</td>\n",
|
|
|
+ " <td>cyclical</td>\n",
|
|
|
+ " </tr>\n",
|
|
|
+ " </tbody>\n",
|
|
|
+ "</table>\n",
|
|
|
+ "</div>"
|
|
|
+ ],
|
|
|
+ "text/plain": [
|
|
|
+ " predicted actual model features\n",
|
|
|
+ "timestamp \n",
|
|
|
+ "2016-01-02 22:45:00 135.545103 71.810619 RandomForestRegressor cyclical\n",
|
|
|
+ "2016-01-02 23:00:00 144.112047 96.005072 RandomForestRegressor cyclical\n",
|
|
|
+ "2016-01-02 23:15:00 144.322802 93.704430 RandomForestRegressor cyclical\n",
|
|
|
+ "2016-01-02 23:30:00 143.739093 94.853490 RandomForestRegressor cyclical\n",
|
|
|
+ "2016-01-02 23:45:00 140.805196 92.931160 RandomForestRegressor cyclical"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ "execution_count": 41,
|
|
|
+ "metadata": {},
|
|
|
+ "output_type": "execute_result"
|
|
|
+ }
|
|
|
+ ],
|
|
|
+ "source": [
|
|
|
+ "validation = pd.concat(validation)\n",
|
|
|
+ "validation.head()\n",
|
|
|
+ "validation.tail()"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 43,
|
|
|
+ "metadata": {},
|
|
|
+ "outputs": [
|
|
|
+ {
|
|
|
+ "data": {
|
|
|
+ "text/plain": [
|
|
|
+ "array(['LinearRegression', 'RandomForestRegressor'], dtype=object)"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ "execution_count": 43,
|
|
|
+ "metadata": {},
|
|
|
+ "output_type": "execute_result"
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "data": {
|
|
|
+ "text/plain": [
|
|
|
+ "array(['standard', 'cyclical'], dtype=object)"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ "execution_count": 43,
|
|
|
+ "metadata": {},
|
|
|
+ "output_type": "execute_result"
|
|
|
+ }
|
|
|
+ ],
|
|
|
+ "source": [
|
|
|
+ "validation['model'].unique()\n",
|
|
|
+ "validation['features'].unique()"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 42,
|
|
|
+ "metadata": {},
|
|
|
+ "outputs": [],
|
|
|
+ "source": [
|
|
|
+ "from IPython.core.interactiveshell import InteractiveShell\n",
|
|
|
+ "InteractiveShell.ast_node_interactivity = 'all'"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 38,
|
|
|
+ "metadata": {},
|
|
|
+ "outputs": [
|
|
|
+ {
|
|
|
+ "data": {
|
|
|
+ "text/plain": [
|
|
|
+ "array(['LinearRegression'], dtype=object)"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ "execution_count": 38,
|
|
|
+ "metadata": {},
|
|
|
+ "output_type": "execute_result"
|
|
|
+ }
|
|
|
+ ],
|
|
|
+ "source": [
|
|
|
+ "validation['model'].unique()"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 11,
|
|
|
+ "metadata": {},
|
|
|
+ "outputs": [],
|
|
|
+ "source": [
|
|
|
+ "def calculate_results(results):\n",
|
|
|
+ " pass"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 12,
|
|
|
+ "metadata": {},
|
|
|
+ "outputs": [],
|
|
|
+ "source": [
|
|
|
+ "def graph_results(results):\n",
|
|
|
+ " pass"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
"execution_count": null,
|
|
|
"metadata": {},
|
|
|
"outputs": [],
|
Will K