{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Module 8\n", "\n", "## Video 34: Hypothesis Testing I\n", "**Python for the Energy Industry**\n", "\n", "If we have a hypothesis about how two variables are related, we may wish to test this hypothesis statistically using data from the SDK. In this lesson and the next, we will see how to do this. This first lesson focuses on looking at the correlation between time series data.\n", "\n", "[Here is a good example of these concepts applied.](https://github.com/VorTECHsa/python-sdk/blob/master/docs/examples/Crude_Floating_Storage.ipynb)" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "# initial imports\n", "import pandas as pd\n", "import numpy as np\n", "from datetime import datetime\n", "from dateutil.relativedelta import relativedelta\n", "import vortexasdk as v\n", "# The cargo unit for the time series (barrels)\n", "TS_UNIT = 'b'\n", "\n", "# The granularity of the time series\n", "TS_FREQ = 'day'\n", "\n", "# datetimes to access last 7 weeks of data\n", "now = datetime.utcnow()\n", "seven_weeks_ago = now - relativedelta(weeks=7)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We will consider a fairly trivial example here to demonstrate the process - let's say we want to consider the correlation between crude exports out of Southeast Asia destined for China, with the crude imports into China that originated in Southeast Asia. These are clearly strongly correlated, with a time lag that depends on travel time. Let's start by accessing these exports and imports datasets:" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "crude = [p.id for p in v.Products().search('crude').to_list() if p.name=='Crude']\n", "assert len(crude) == 1\n", "\n", "china = v.Geographies().search('China',exact_term_match=True)[0]['id']\n", "SEA = v.Geographies().search('Southeast Asia',exact_term_match=True)[0]['id']\n", "\n", "SEA_exports = v.CargoTimeSeries().search(\n", " timeseries_frequency=TS_FREQ,\n", " timeseries_unit=TS_UNIT,\n", " filter_time_min=seven_weeks_ago,\n", " filter_time_max=now,\n", " filter_activity=\"loading_end\",\n", " filter_origins=SEA,\n", " filter_destinations=china,\n", ").to_df()\n", "\n", "SEA_exports = SEA_exports.rename(columns={'key':'date','value':'SEA_exp'})[['date','SEA_exp']]" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "china_imports = v.CargoTimeSeries().search(\n", " timeseries_frequency=TS_FREQ,\n", " timeseries_unit=TS_UNIT,\n", " filter_time_min=seven_weeks_ago,\n", " filter_time_max=now,\n", " filter_activity=\"unloading_start\",\n", " filter_origins=SEA,\n", " filter_destinations=china,\n", ").to_df()\n", "\n", "china_imports = china_imports.rename(columns={'key':'date','value':'china_imp'})[['date','china_imp']]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Combine the exports and imports data into one DataFrame:" ] }, { "cell_type": "code", "execution_count": 4, "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", "
dateSEA_expchina_imp
02020-10-23 00:00:00+00:0013228322670087
12020-10-24 00:00:00+00:0035626552940471
22020-10-25 00:00:00+00:0043142602373007
32020-10-26 00:00:00+00:0042778801440071
42020-10-27 00:00:00+00:0036184041614060
\n", "
" ], "text/plain": [ " date SEA_exp china_imp\n", "0 2020-10-23 00:00:00+00:00 1322832 2670087\n", "1 2020-10-24 00:00:00+00:00 3562655 2940471\n", "2 2020-10-25 00:00:00+00:00 4314260 2373007\n", "3 2020-10-26 00:00:00+00:00 4277880 1440071\n", "4 2020-10-27 00:00:00+00:00 3618404 1614060" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "combined_df = SEA_exports\n", "combined_df['china_imp'] = china_imports['china_imp']\n", "\n", "# use dropna in case any NaN results are returned by the query\n", "combined_df = combined_df.dropna()\n", "\n", "combined_df.head()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Lets take a look at our two datasets and see if they look correlated:" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "combined_df.plot(x='date',y=['china_imp','SEA_exp'])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "It looks like they might be correlated, but to be sure we'll want to calculate the cross-correlation between the time series as a function of the number of lags. Let's write a function to do that:" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "def crosscorr(x, y, lag):\n", " return x.corr(y.shift(lag))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We then calculate the cross correlation between the two time series, across a range of lags up to 20 days in each direction. These values are put into a DataFrame and plotted:" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "lags = np.arange(-20,20)\n", "ccs = [crosscorr(combined_df['china_imp'], combined_df['SEA_exp'], lag) for lag in lags]\n", "ccs_df = pd.DataFrame(ccs,index=lags)\n", "ccs_df.plot()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "*Note: [here is](https://www.usna.edu/Users/oceano/pguth/md_help/html/time0alq.htm) a good reference for a bit more detail on interpreting cross-correlation plots.*\n", "\n", "Cross-correlation is difficult to interpret, because it can reflect autocorrelations within each time series. We can plot the cross-correlation of each time series with itself to get the autocorrelation:" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "lags = np.arange(0,20)\n", "acs1 = [crosscorr(combined_df['china_imp'], combined_df['china_imp'], lag) for lag in lags]\n", "acs_df1 = pd.DataFrame(acs1,index=lags)\n", "acs_df1.plot()" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "acs2 = [crosscorr(combined_df['SEA_exp'], combined_df['SEA_exp'], lag) for lag in lags]\n", "acs_df2 = pd.DataFrame(acs2,index=lags)\n", "acs_df2.plot()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We do indeed see that within each time series there is autocorrelation both on the short term, but also at longer time scales. We will need to do something else to disentagle this." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Exercise\n", "\n", "Pick 2 time series data sets that you would *not* expect to be correlated. Do the cross-correlation and autocorrelation plots confirm this?" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "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": "3.7.9" } }, "nbformat": 4, "nbformat_minor": 4 }