diff --git a/wk7/wk7.ipynb b/wk7/wk7.ipynb index c94124c..a7dd198 100644 --- a/wk7/wk7.ipynb +++ b/wk7/wk7.ipynb @@ -9,16 +9,27 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 2, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "Using matplotlib backend: MacOSX\n", + "Using matplotlib backend: TkAgg\n", "Populating the interactive namespace from numpy and matplotlib\n" ] + }, + { + "ename": "ImportError", + "evalue": "No module named 'seaborn'", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mImportError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[0mget_ipython\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmagic\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'matplotlib inline'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mpandas\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m \u001b[0;32mimport\u001b[0m \u001b[0mseaborn\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0msn\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 5\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mnumpy\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 6\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mmatplotlib\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpyplot\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mplt\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mImportError\u001b[0m: No module named 'seaborn'" + ] } ], "source": [ @@ -35,196 +46,19 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 1, "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", - "
rankingagepointstournplayedbornweightheight
ranking1-0.165935-0.586707-0.2440730.17403-0.08260930.0196139
age-0.16593510.121731-0.140033-0.9942960.157223-0.0282972
points-0.5867070.1217311-0.004905-0.1299710.159385-0.0153843
tournplayed-0.244073-0.140033-0.00490510.13293-0.139194-0.0712482
born0.17403-0.994296-0.1299710.132931-0.1636770.0333731
weight-0.08260930.1572230.159385-0.139194-0.16367710.757689
height0.0196139-0.0282972-0.0153843-0.07124820.03337310.7576891
" - ], - "text/plain": [ - "" - ] - }, - "execution_count": 2, - "metadata": {}, - "output_type": "execute_result" + "ename": "NameError", + "evalue": "name 'data' is not defined", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mdata\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcorr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstyle\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbackground_gradient\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcmap\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'Wistia'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", + "\u001b[0;31mNameError\u001b[0m: name 'data' is not defined" + ] } ], "source": [ diff --git a/wk8/wk8.ipynb b/wk8/wk8.ipynb index 68a5eae..3d3860d 100644 --- a/wk8/wk8.ipynb +++ b/wk8/wk8.ipynb @@ -40,31 +40,29 @@ "\n", "**\\*\\* Double Check this with Murray \\*\\***\n", "\n", - "\\*\\* Now we need to read the excel file in a nice way given that the spreadsheet has double headings in some places" + "TO DO:\n", + "\\*\\* Need to test the statistical significance of the data" ] }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 19, "metadata": {}, "outputs": [], "source": [ - "data = pd.read_excel('Dong_etal_2018_data.xlsx', sheetname='A1')" + "# Contains data about the number of customers during the recorded time period\n", + "cust_data = pd.read_excel('edited_Dong_etal_2018_data.xlsx', sheetname='# of Customers')\n", + "# Contains data about the customers' median spending amounts during the recorded time period\n", + "spend_data = pd.read_excel('edited_Dong_etal_2018_data.xlsx', sheetname='Median spending amount')\n", + "# Contains data about the number of transactions during the recorded time period\n", + "trans_data = pd.read_excel('edited_Dong_etal_2018_data.xlsx', sheetname='# of transactions')" ] }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 17, "metadata": {}, "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/usr/local/lib/python3.5/dist-packages/matplotlib/colors.py:494: RuntimeWarning: invalid value encountered in less\n", - " cbook._putmask(xa, xa < 0.0, -1)\n" - ] - }, { "data": { "text/html": [ @@ -72,159 +70,105 @@ " \n", "\n", - " \n", + "
\n", " \n", "\n", " \n", @@ -243,22 +187,17 @@ " \n", " \n", " \n", @@ -269,39 +208,33 @@ " \n", " \n", " \n", - " \n", @@ -309,39 +242,33 @@ " \n", " \n", " \n", - " \n", @@ -349,39 +276,33 @@ " \n", " \n", " \n", - " \n", @@ -389,79 +310,33 @@ " \n", " \n", " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", @@ -471,25 +346,46 @@ " " ], "text/plain": [ - "" + "" ] }, - "execution_count": 14, + "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "data.corr().style.background_gradient(cmap='Wistia')" + "cust_data.corr().style.background_gradient(cmap='Wistia')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ - "****\\*\\*\\*\\* We gon' need to get rid of some of them headins' \\*\\*\\*\\* ****" + "Now to plot some data..." ] }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, { "cell_type": "markdown", "metadata": {},
\n", - " Unnamed: 1\n", + " Min of ref. Days\n", " \n", " \n", " \n", " \n", - " Unnamed: 5\n", + " Max of ref. Days\n", " \n", " \n", " \n", " \n", - " Unnamed: 9\n", - " \n", - " \n", - " \n", - " \n", - " Unnamed: 13\n", + " Decrease on Day 62\n", " \n", " \n", "
\n", " Distance from event center (km)\n", " \n", " \n", " \n", - " \n", " 1\n", " \n", " \n", " \n", - " \n", - " nan\n", + " -0.104681\n", " \n", " \n", " \n", - " \n", - " nan\n", + " -0.101477\n", " \n", " \n", " \n", - " \n", - " nan\n", - " \n", - " \n", - " \n", - " \n", - " nan\n", + " -0.375261\n", " \n", " \n", "
\n", - " Unnamed: 1\n", + " Min of ref. Days\n", " \n", " \n", " \n", - " \n", - " nan\n", + " -0.104681\n", " \n", " \n", " \n", - " \n", - " nan\n", + " 1\n", " \n", " \n", " \n", - " \n", - " nan\n", + " 0.990716\n", " \n", " \n", " \n", - " \n", - " nan\n", - " \n", - " \n", - " \n", - " \n", - " nan\n", + " 0.855398\n", " \n", " \n", "
\n", - " Unnamed: 5\n", + " Max of ref. Days\n", " \n", " \n", " \n", - " \n", - " nan\n", + " -0.101477\n", " \n", " \n", " \n", - " \n", - " nan\n", + " 0.990716\n", " \n", " \n", " \n", - " \n", - " nan\n", + " 1\n", " \n", " \n", " \n", - " \n", - " nan\n", - " \n", - " \n", - " \n", - " \n", - " nan\n", + " 0.869914\n", " \n", " \n", "
\n", - " Unnamed: 9\n", + " Decrease on Day 62\n", " \n", " \n", " \n", - " \n", - " nan\n", + " -0.375261\n", " \n", " \n", " \n", - " \n", - " nan\n", + " 0.855398\n", " \n", " \n", " \n", - " \n", - " nan\n", + " 0.869914\n", " \n", " \n", " \n", - " \n", - " nan\n", - " \n", - " \n", - " \n", - " \n", - " nan\n", - " \n", - " \n", - "
\n", - " Unnamed: 13\n", - " \n", - " \n", - " \n", - " \n", - " nan\n", - " \n", - " \n", - " \n", - " \n", - " nan\n", - " \n", - " \n", - " \n", - " \n", - " nan\n", - " \n", - " \n", - " \n", - " \n", - " nan\n", - " \n", - " \n", - " \n", - " \n", - " nan\n", + " 1\n", " \n", " \n", "