mirror of
https://github.com/saymrwulf/prophet.git
synced 2026-06-25 02:50:49 +00:00
353 lines
101 KiB
Text
353 lines
101 KiB
Text
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {
|
|
"block_hidden": true
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"%load_ext rpy2.ipython\n",
|
|
"%matplotlib inline\n",
|
|
"from prophet import Prophet\n",
|
|
"import pandas as pd\n",
|
|
"from matplotlib import pyplot as plt\n",
|
|
"import numpy as np\n",
|
|
"import logging\n",
|
|
"logging.getLogger('prophet').setLevel(logging.ERROR)\n",
|
|
"import warnings\n",
|
|
"warnings.filterwarnings(\"ignore\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {
|
|
"block_hidden": true
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"INFO:numexpr.utils:NumExpr defaulting to 8 threads.\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"df = pd.read_csv('../examples/example_wp_log_peyton_manning.csv')\n",
|
|
"df = df.loc[:180,] # Limit to first six months\n",
|
|
"m = Prophet()\n",
|
|
"m.fit(df)\n",
|
|
"future = m.make_future_dataframe(periods=60)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {
|
|
"block_hidden": true
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"R[write to console]: Loading required package: Rcpp\n",
|
|
"\n",
|
|
"R[write to console]: Loading required package: rlang\n",
|
|
"\n",
|
|
"R[write to console]: Disabling yearly seasonality. Run prophet with yearly.seasonality=TRUE to override this.\n",
|
|
"\n",
|
|
"R[write to console]: Disabling daily seasonality. Run prophet with daily.seasonality=TRUE to override this.\n",
|
|
"\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"%%R\n",
|
|
"library(prophet)\n",
|
|
"df <- read.csv('../examples/example_wp_log_peyton_manning.csv')\n",
|
|
"df <- df[1:180,]\n",
|
|
"m <- prophet(df)\n",
|
|
"future <- make_future_dataframe(m, periods=60)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"By default Prophet will return uncertainty intervals for the forecast `yhat`. There are several important assumptions behind these uncertainty intervals.\n",
|
|
"\n",
|
|
"There are three sources of uncertainty in the forecast: uncertainty in the trend, uncertainty in the seasonality estimates, and additional observation noise.\n",
|
|
"\n",
|
|
"### Uncertainty in the trend\n",
|
|
"The biggest source of uncertainty in the forecast is the potential for future trend changes. The time series we have seen already in this documentation show clear trend changes in the history. Prophet is able to detect and fit these, but what trend changes should we expect moving forward? It's impossible to know for sure, so we do the most reasonable thing we can, and we assume that the *future will see similar trend changes as the history*. In particular, we assume that the average frequency and magnitude of trend changes in the future will be the same as that which we observe in the history. We project these trend changes forward and by computing their distribution we obtain uncertainty intervals.\n",
|
|
"\n",
|
|
"One property of this way of measuring uncertainty is that allowing higher flexibility in the rate, by increasing `changepoint_prior_scale`, will increase the forecast uncertainty. This is because if we model more rate changes in the history then we will expect more in the future, and makes the uncertainty intervals a useful indicator of overfitting.\n",
|
|
"\n",
|
|
"The width of the uncertainty intervals (by default 80%) can be set using the parameter `interval_width`:"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {
|
|
"output_hidden": true
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"R[write to console]: Disabling yearly seasonality. Run prophet with yearly.seasonality=TRUE to override this.\n",
|
|
"\n",
|
|
"R[write to console]: Disabling daily seasonality. Run prophet with daily.seasonality=TRUE to override this.\n",
|
|
"\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"%%R\n",
|
|
"m <- prophet(df, interval.width = 0.95)\n",
|
|
"forecast <- predict(m, future)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"forecast = Prophet(interval_width=0.95).fit(df).predict(future)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"Again, these intervals assume that the future will see the same frequency and magnitude of rate changes as the past. This assumption is probably not true, so you should not expect to get accurate coverage on these uncertainty intervals.\n",
|
|
"\n",
|
|
"### Uncertainty in seasonality\n",
|
|
"By default Prophet will only return uncertainty in the trend and observation noise. To get uncertainty in seasonality, you must do full Bayesian sampling. This is done using the parameter `mcmc.samples` (which defaults to 0). We do this here for the first six months of the Peyton Manning data from the Quickstart:"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {
|
|
"output_hidden": true
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"R[write to console]: Disabling yearly seasonality. Run prophet with yearly.seasonality=TRUE to override this.\n",
|
|
"\n",
|
|
"R[write to console]: Disabling daily seasonality. Run prophet with daily.seasonality=TRUE to override this.\n",
|
|
"\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"\n",
|
|
"SAMPLING FOR MODEL 'prophet' NOW (CHAIN 1).\n",
|
|
"Chain 1: \n",
|
|
"Chain 1: Gradient evaluation took 8.6e-05 seconds\n",
|
|
"Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 0.86 seconds.\n",
|
|
"Chain 1: Adjust your expectations accordingly!\n",
|
|
"Chain 1: \n",
|
|
"Chain 1: \n",
|
|
"Chain 1: Iteration: 1 / 300 [ 0%] (Warmup)\n",
|
|
"Chain 1: Iteration: 30 / 300 [ 10%] (Warmup)\n",
|
|
"Chain 1: Iteration: 60 / 300 [ 20%] (Warmup)\n",
|
|
"Chain 1: Iteration: 90 / 300 [ 30%] (Warmup)\n",
|
|
"Chain 1: Iteration: 120 / 300 [ 40%] (Warmup)\n",
|
|
"Chain 1: Iteration: 150 / 300 [ 50%] (Warmup)\n",
|
|
"Chain 1: Iteration: 151 / 300 [ 50%] (Sampling)\n",
|
|
"Chain 1: Iteration: 180 / 300 [ 60%] (Sampling)\n",
|
|
"Chain 1: Iteration: 210 / 300 [ 70%] (Sampling)\n",
|
|
"Chain 1: Iteration: 240 / 300 [ 80%] (Sampling)\n",
|
|
"Chain 1: Iteration: 270 / 300 [ 90%] (Sampling)\n",
|
|
"Chain 1: Iteration: 300 / 300 [100%] (Sampling)\n",
|
|
"Chain 1: \n",
|
|
"Chain 1: Elapsed Time: 2.10541 seconds (Warm-up)\n",
|
|
"Chain 1: 2.37589 seconds (Sampling)\n",
|
|
"Chain 1: 4.4813 seconds (Total)\n",
|
|
"Chain 1: \n",
|
|
"\n",
|
|
"SAMPLING FOR MODEL 'prophet' NOW (CHAIN 2).\n",
|
|
"Chain 2: \n",
|
|
"Chain 2: Gradient evaluation took 7.4e-05 seconds\n",
|
|
"Chain 2: 1000 transitions using 10 leapfrog steps per transition would take 0.74 seconds.\n",
|
|
"Chain 2: Adjust your expectations accordingly!\n",
|
|
"Chain 2: \n",
|
|
"Chain 2: \n",
|
|
"Chain 2: Iteration: 1 / 300 [ 0%] (Warmup)\n",
|
|
"Chain 2: Iteration: 30 / 300 [ 10%] (Warmup)\n",
|
|
"Chain 2: Iteration: 60 / 300 [ 20%] (Warmup)\n",
|
|
"Chain 2: Iteration: 90 / 300 [ 30%] (Warmup)\n",
|
|
"Chain 2: Iteration: 120 / 300 [ 40%] (Warmup)\n",
|
|
"Chain 2: Iteration: 150 / 300 [ 50%] (Warmup)\n",
|
|
"Chain 2: Iteration: 151 / 300 [ 50%] (Sampling)\n",
|
|
"Chain 2: Iteration: 180 / 300 [ 60%] (Sampling)\n",
|
|
"Chain 2: Iteration: 210 / 300 [ 70%] (Sampling)\n",
|
|
"Chain 2: Iteration: 240 / 300 [ 80%] (Sampling)\n",
|
|
"Chain 2: Iteration: 270 / 300 [ 90%] (Sampling)\n",
|
|
"Chain 2: Iteration: 300 / 300 [100%] (Sampling)\n",
|
|
"Chain 2: \n",
|
|
"Chain 2: Elapsed Time: 2.04288 seconds (Warm-up)\n",
|
|
"Chain 2: 2.12795 seconds (Sampling)\n",
|
|
"Chain 2: 4.17083 seconds (Total)\n",
|
|
"Chain 2: \n",
|
|
"\n",
|
|
"SAMPLING FOR MODEL 'prophet' NOW (CHAIN 3).\n",
|
|
"Chain 3: \n",
|
|
"Chain 3: Gradient evaluation took 7.1e-05 seconds\n",
|
|
"Chain 3: 1000 transitions using 10 leapfrog steps per transition would take 0.71 seconds.\n",
|
|
"Chain 3: Adjust your expectations accordingly!\n",
|
|
"Chain 3: \n",
|
|
"Chain 3: \n",
|
|
"Chain 3: Iteration: 1 / 300 [ 0%] (Warmup)\n",
|
|
"Chain 3: Iteration: 30 / 300 [ 10%] (Warmup)\n",
|
|
"Chain 3: Iteration: 60 / 300 [ 20%] (Warmup)\n",
|
|
"Chain 3: Iteration: 90 / 300 [ 30%] (Warmup)\n",
|
|
"Chain 3: Iteration: 120 / 300 [ 40%] (Warmup)\n",
|
|
"Chain 3: Iteration: 150 / 300 [ 50%] (Warmup)\n",
|
|
"Chain 3: Iteration: 151 / 300 [ 50%] (Sampling)\n",
|
|
"Chain 3: Iteration: 180 / 300 [ 60%] (Sampling)\n",
|
|
"Chain 3: Iteration: 210 / 300 [ 70%] (Sampling)\n",
|
|
"Chain 3: Iteration: 240 / 300 [ 80%] (Sampling)\n",
|
|
"Chain 3: Iteration: 270 / 300 [ 90%] (Sampling)\n",
|
|
"Chain 3: Iteration: 300 / 300 [100%] (Sampling)\n",
|
|
"Chain 3: \n",
|
|
"Chain 3: Elapsed Time: 2.24488 seconds (Warm-up)\n",
|
|
"Chain 3: 2.5196 seconds (Sampling)\n",
|
|
"Chain 3: 4.76448 seconds (Total)\n",
|
|
"Chain 3: \n",
|
|
"\n",
|
|
"SAMPLING FOR MODEL 'prophet' NOW (CHAIN 4).\n",
|
|
"Chain 4: \n",
|
|
"Chain 4: Gradient evaluation took 6.5e-05 seconds\n",
|
|
"Chain 4: 1000 transitions using 10 leapfrog steps per transition would take 0.65 seconds.\n",
|
|
"Chain 4: Adjust your expectations accordingly!\n",
|
|
"Chain 4: \n",
|
|
"Chain 4: \n",
|
|
"Chain 4: Iteration: 1 / 300 [ 0%] (Warmup)\n",
|
|
"Chain 4: Iteration: 30 / 300 [ 10%] (Warmup)\n",
|
|
"Chain 4: Iteration: 60 / 300 [ 20%] (Warmup)\n",
|
|
"Chain 4: Iteration: 90 / 300 [ 30%] (Warmup)\n",
|
|
"Chain 4: Iteration: 120 / 300 [ 40%] (Warmup)\n",
|
|
"Chain 4: Iteration: 150 / 300 [ 50%] (Warmup)\n",
|
|
"Chain 4: Iteration: 151 / 300 [ 50%] (Sampling)\n",
|
|
"Chain 4: Iteration: 180 / 300 [ 60%] (Sampling)\n",
|
|
"Chain 4: Iteration: 210 / 300 [ 70%] (Sampling)\n",
|
|
"Chain 4: Iteration: 240 / 300 [ 80%] (Sampling)\n",
|
|
"Chain 4: Iteration: 270 / 300 [ 90%] (Sampling)\n",
|
|
"Chain 4: Iteration: 300 / 300 [100%] (Sampling)\n",
|
|
"Chain 4: \n",
|
|
"Chain 4: Elapsed Time: 2.2803 seconds (Warm-up)\n",
|
|
"Chain 4: 2.73488 seconds (Sampling)\n",
|
|
"Chain 4: 5.01518 seconds (Total)\n",
|
|
"Chain 4: \n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"%%R\n",
|
|
"m <- prophet(df, mcmc.samples = 300)\n",
|
|
"forecast <- predict(m, future)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"m = Prophet(mcmc_samples=300)\n",
|
|
"forecast = m.fit(df).predict(future)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"This replaces the typical MAP estimation with MCMC sampling, and can take much longer depending on how many observations there are - expect several minutes instead of several seconds. If you do full sampling, then you will see the uncertainty in seasonal components when you plot them:"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {
|
|
"output_hidden": true
|
|
},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"image/png": "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"
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
}
|
|
],
|
|
"source": [
|
|
"%%R -w 9 -h 6 -u in\n",
|
|
"prophet_plot_components(m, forecast)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"image/png": "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",
|
|
"text/plain": [
|
|
"<Figure size 648x432 with 2 Axes>"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
}
|
|
],
|
|
"source": [
|
|
"fig = m.plot_components(forecast)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"You can access the raw posterior predictive samples in Python using the method `m.predictive_samples(future)`, or in R using the function `predictive_samples(m, future)`."
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"celltoolbar": "Edit Metadata",
|
|
"kernelspec": {
|
|
"display_name": "Python 3",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.8.3"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 1
|
|
}
|