New medium stat data

widgets/Widgets Overview.ipynb

@@ -42,11 +42,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-01-25T20:29:08.648989Z",
-     "start_time": "2019-01-25T20:29:08.625762Z"
+     "end_time": "2019-01-26T15:23:54.625835Z",
+     "start_time": "2019-01-26T15:23:54.600697Z"
     }
    },
    "outputs": [],
@@ -57,11 +57,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-01-25T20:29:09.835804Z",
-     "start_time": "2019-01-25T20:29:08.650774Z"
+     "end_time": "2019-01-26T15:23:56.409220Z",
+     "start_time": "2019-01-26T15:23:55.155270Z"
     }
    },
    "outputs": [
@@ -139,11 +139,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-01-25T20:29:10.769888Z",
-     "start_time": "2019-01-25T20:29:09.837243Z"
+     "end_time": "2019-01-26T15:23:57.165729Z",
+     "start_time": "2019-01-26T15:23:56.438408Z"
     }
    },
    "outputs": [
@@ -405,7 +405,7 @@
        "114                      0            0  "
       ]
      },
-     "execution_count": 4,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     },
@@ -666,7 +666,7 @@
        "max       1.000000  "
       ]
      },
-     "execution_count": 4,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -682,11 +682,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-01-25T20:29:10.798302Z",
-     "start_time": "2019-01-25T20:29:10.771282Z"
+     "end_time": "2019-01-26T15:23:57.235398Z",
+     "start_time": "2019-01-26T15:23:57.209251Z"
     }
    },
    "outputs": [],
@@ -704,23 +704,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 8,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-01-25T20:29:11.016195Z",
-     "start_time": "2019-01-25T20:29:10.800459Z"
+     "end_time": "2019-01-26T15:25:58.282884Z",
+     "start_time": "2019-01-26T15:25:58.226592Z"
     }
    },
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "184bebd9a6254378bb451b7141bcb2b7",
+       "model_id": "e6d50986487449339d2104305e066517",
        "version_major": 2,
        "version_minor": 0
       },
       "text/plain": [
-       "interactive(children=(Dropdown(description='Choose Image', options=('iscatter.gif', 'Screen Shot 2019-01-08 at…"
+       "interactive(children=(Dropdown(description='file', options=('1080_1189866210-spanish-sunset.jpg', '1080_201401…"
       ]
      },
      "metadata": {},
@@ -728,13 +728,11 @@
     }
    ],
    "source": [
-    "fdir = 'images/'\n",
+    "fdir = 'nature/'\n",
     "\n",
-    "def show_images(file):\n",
-    "    display(Image(fdir+file))\n",
-    "    \n",
-    "selection = widgets.Dropdown(options=os.listdir(fdir), description='Choose Image')\n",
-    "show_images_interact = interact(show_images, file=selection)"
+    "@interact\n",
+    "def show_images(file=os.listdir(fdir)):\n",
+    "    display(Image(fdir+file))"
    ]
   },
   {
@@ -746,11 +744,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 9,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-01-25T20:29:11.185114Z",
-     "start_time": "2019-01-25T20:29:11.018786Z"
+     "end_time": "2019-01-26T15:26:12.510418Z",
+     "start_time": "2019-01-26T15:26:12.338506Z"
     }
    },
    "outputs": [
@@ -758,13 +756,14 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "total 104\r\n",
-      "drwxr-xr-x  36 williamkoehrsen  staff   1152 Jan 22 19:47 \u001b[34m..\u001b[m\u001b[m\r\n",
-      "drwxr-xr-x   3 williamkoehrsen  staff     96 Jan 22 19:50 \u001b[34m.ipynb_checkpoints\u001b[m\u001b[m\r\n",
-      "drwxr-xr-x  41 williamkoehrsen  staff   1312 Jan 25 14:43 \u001b[34mimages\u001b[m\u001b[m\r\n",
-      "-rw-r--r--@  1 williamkoehrsen  staff   6148 Jan 25 14:51 .DS_Store\r\n",
-      "-rw-r--r--   1 williamkoehrsen  staff  43174 Jan 25 15:28 Widgets Overview.ipynb\r\n",
-      "drwxr-xr-x   6 williamkoehrsen  staff    192 Jan 25 15:28 \u001b[34m.\u001b[m\u001b[m\r\n"
+      "total 11680\r\n",
+      "drwxr-xr-x  36 williamkoehrsen  staff     1152 Jan 22 19:47 \u001b[34m..\u001b[m\u001b[m\r\n",
+      "drwxr-xr-x   3 williamkoehrsen  staff       96 Jan 22 19:50 \u001b[34m.ipynb_checkpoints\u001b[m\u001b[m\r\n",
+      "drwxr-xr-x  26 williamkoehrsen  staff      832 Jan 26 10:09 \u001b[34mnature\u001b[m\u001b[m\r\n",
+      "-rw-r--r--   1 williamkoehrsen  staff  5968133 Jan 26 10:24 Widgets Overview.ipynb\r\n",
+      "-rw-r--r--@  1 williamkoehrsen  staff     6148 Jan 26 10:25 .DS_Store\r\n",
+      "drwxr-xr-x   7 williamkoehrsen  staff      224 Jan 26 10:25 \u001b[34m.\u001b[m\u001b[m\r\n",
+      "drwxr-xr-x  41 williamkoehrsen  staff     1312 Jan 26 10:25 \u001b[34mimages\u001b[m\u001b[m\r\n"
      ]
     }
    ],
@@ -774,23 +773,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 10,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-01-25T20:29:11.256164Z",
-     "start_time": "2019-01-25T20:29:11.187251Z"
+     "end_time": "2019-01-26T15:26:48.070489Z",
+     "start_time": "2019-01-26T15:26:47.994664Z"
     }
    },
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "cde5cc28506d488bbbd00e031d1fd72b",
+       "model_id": "2c292cfbe6f94b0b99e0a38df42159b0",
        "version_major": 2,
        "version_minor": 0
       },
       "text/plain": [
-       "interactive(children=(Dropdown(description='Directory', index=19, options=('additive_models', 'statistics', 'r…"
+       "interactive(children=(Dropdown(description='dir', options=('additive_models', 'statistics', 'recall_precision'…"
       ]
      },
      "metadata": {},
@@ -803,21 +802,19 @@
     "\n",
     "root_dir = '../../Data-Analysis/'\n",
     "\n",
-    "def show_dir(dir):\n",
+    "@interact\n",
+    "def show_dir(dir=os.listdir(root_dir)):\n",
     "    x = subprocess.check_output(f\"cd {root_dir}{dir} && ls -a -t -r -l -h\", shell=True).decode()\n",
-    "    print(x)\n",
-    "\n",
-    "    \n",
-    "file_browser = interact(show_dir, dir=widgets.Dropdown(options=os.listdir(root_dir), value='bayesian_lr', description='Directory'))"
+    "    print(x)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 11,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-01-25T20:29:11.292813Z",
-     "start_time": "2019-01-25T20:29:11.258044Z"
+     "end_time": "2019-01-26T15:27:18.237729Z",
+     "start_time": "2019-01-26T15:27:18.199821Z"
     }
    },
    "outputs": [],
@@ -835,18 +832,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 13,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-01-25T20:29:11.404157Z",
-     "start_time": "2019-01-25T20:29:11.294967Z"
+     "end_time": "2019-01-26T15:27:48.094422Z",
+     "start_time": "2019-01-26T15:27:48.027048Z"
     }
    },
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "dfcd31e2f286493bb3166d49a76f4f02",
+       "model_id": "ef174a13a0d84031b35c857ff553afb7",
        "version_major": 2,
        "version_minor": 0
       },
@@ -859,28 +856,26 @@
     }
    ],
    "source": [
-    "def correlations(column1, column2):\n",
-    "    print(f\"Correlation: {df[column1].corr(df[column2])}\")\n",
-    "    \n",
-    "corr_interact = interact(correlations, \n",
-    "         column1 = widgets.Dropdown(options=list(df.select_dtypes('number').columns)),\n",
-    "         column2=widgets.Dropdown(options=list(df.select_dtypes('number').columns)))"
+    "@interact\n",
+    "def correlations(column1=list(df.select_dtypes('number').columns), \n",
+    "                 column2=list(df.select_dtypes('number').columns)):\n",
+    "    print(f\"Correlation: {df[column1].corr(df[column2])}\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 14,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-01-25T20:29:11.463615Z",
-     "start_time": "2019-01-25T20:29:11.406271Z"
+     "end_time": "2019-01-26T15:28:05.685384Z",
+     "start_time": "2019-01-26T15:28:05.634449Z"
     }
    },
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "b83a9974e79b497e93051cfca6d58651",
+       "model_id": "2995521ecbe244bd8a766b57aaa8592e",
        "version_major": 2,
        "version_minor": 0
       },
@@ -900,23 +895,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 15,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-01-25T20:29:12.213722Z",
-     "start_time": "2019-01-25T20:29:11.465380Z"
+     "end_time": "2019-01-26T15:28:37.479840Z",
+     "start_time": "2019-01-26T15:28:36.754516Z"
     }
    },
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "26b5b73bc0aa457eb1d6ef78025eae3a",
+       "model_id": "75a1c54f686e475e83f7b14e896c9823",
        "version_major": 2,
        "version_minor": 0
       },
       "text/plain": [
-       "interactive(children=(Dropdown(description='x', index=2, options=('claps', 'days_since_publication', 'fans', '…"
+       "interactive(children=(Dropdown(description='x', options=('claps', 'days_since_publication', 'fans', 'num_respo…"
       ]
      },
      "metadata": {},
@@ -924,21 +919,20 @@
     }
    ],
    "source": [
-    "def scatter_plot(x, y):\n",
-    "    df.iplot(kind='scatter', x=x, y=y, mode='markers', # colors=['red'],\n",
-    "             xTitle=x.title(), yTitle=y.title(), title=f'{y.title()} vs {x.title()}')\n",
-    "    \n",
-    "scatter_interact = interact(scatter_plot, x = widgets.Dropdown(options=list(df.select_dtypes('number').columns), value='fans'),\n",
-    "                                          y=widgets.Dropdown(options=list(df.select_dtypes('number').columns), value='num_responses'))"
+    "@interact\n",
+    "def scatter_plot(x=list(df.select_dtypes('number').columns), \n",
+    "                 y=list(df.select_dtypes('number').columns)[1:]):\n",
+    "    df.iplot(kind='scatter', x=x, y=y, mode='markers', \n",
+    "             xTitle=x.title(), yTitle=y.title(), title=f'{y.title()} vs {x.title()}')"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 16,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-01-25T20:29:12.257929Z",
-     "start_time": "2019-01-25T20:29:12.215180Z"
+     "end_time": "2019-01-26T15:28:45.774058Z",
+     "start_time": "2019-01-26T15:28:45.728288Z"
     }
    },
    "outputs": [],
@@ -948,30 +942,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2019-01-25T20:18:18.259995Z",
-     "start_time": "2019-01-25T20:18:18.214782Z"
-    }
-   },
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 17,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-01-25T20:29:12.429125Z",
-     "start_time": "2019-01-25T20:29:12.259365Z"
+     "end_time": "2019-01-26T15:28:47.624352Z",
+     "start_time": "2019-01-26T15:28:47.321009Z"
     }
    },
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "aeb819df311f4b7299bd04ff8055f4f5",
+       "model_id": "18a663de379f4a0a914e63d6b91d995c",
        "version_major": 2,
        "version_minor": 0
       },
@@ -999,18 +981,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 20,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-01-25T20:29:12.844467Z",
-     "start_time": "2019-01-25T20:29:12.430431Z"
+     "end_time": "2019-01-26T15:30:53.530182Z",
+     "start_time": "2019-01-26T15:30:53.203768Z"
     }
    },
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "0bbe31915cd1455aa8c14b0deeb55896",
+       "model_id": "0d3cf61e00c9416cb2873fd715ecb9a2",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1026,14 +1008,18 @@
     "df['binned_read_time'] = pd.cut(df['read_time'], bins=range(0, 56, 5))\n",
     "df['binned_read_time'] = df['binned_read_time'].astype(str)\n",
     "\n",
+    "df['binned_word_count'] = pd.cut(df['word_count'], bins=range(0, 100001, 1000))\n",
+    "df['binned_word_count'] = df['binned_word_count'].astype(str)\n",
+    "\n",
     "@interact\n",
     "def scatter_plot(x=list(df.select_dtypes('number').columns), \n",
     "                 y=list(df.select_dtypes('number').columns)[1:],\n",
+    "                 categories=['binned_read_time', 'binned_word_count', 'publication', 'type'],\n",
     "                 theme=list(cf.themes.THEMES.keys()), \n",
     "                 colorscale=list(cf.colors._scales_names.keys())):\n",
     "    \n",
     "    df.iplot(kind='scatter', x=x, y=y, mode='markers', \n",
-    "             categories='binned_read_time', \n",
+    "             categories=categories, \n",
     "             xTitle=x.title(), yTitle=y.title(), \n",
     "             text='title',\n",
     "             title=f'{y.title()} vs {x.title()}',\n",
@@ -1042,11 +1028,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 21,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-01-25T20:29:12.889801Z",
-     "start_time": "2019-01-25T20:29:12.846095Z"
+     "end_time": "2019-01-26T15:31:08.047748Z",
+     "start_time": "2019-01-26T15:31:08.001162Z"
     }
    },
    "outputs": [],
@@ -1056,18 +1042,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 22,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-01-25T20:29:12.981824Z",
-     "start_time": "2019-01-25T20:29:12.891447Z"
+     "end_time": "2019-01-26T15:31:15.377246Z",
+     "start_time": "2019-01-26T15:31:15.271903Z"
     }
    },
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "7c18ebc81f674ea2a1915f7af83b40d5",
+       "model_id": "729d376c1079467ab73ada470796e1c4",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1083,11 +1069,12 @@
     "@interact_manual\n",
     "def scatter_plot(x=list(df.select_dtypes('number').columns), \n",
     "                 y=list(df.select_dtypes('number').columns)[1:],\n",
+    "                 categories=['binned_read_time', 'binned_word_count', 'publication', 'type'],\n",
     "                 theme=list(cf.themes.THEMES.keys()), \n",
     "                 colorscale=list(cf.colors._scales_names.keys())):\n",
     "    \n",
     "    df.iplot(kind='scatter', x=x, y=y, mode='markers', \n",
-    "             categories='binned_read_time', \n",
+    "             categories=categories, \n",
     "             xTitle=x.title(), yTitle=y.title(), \n",
     "             text='title',\n",
     "             title=f'{y.title()} vs {x.title()}',\n",
@@ -1096,11 +1083,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 23,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-01-25T20:29:13.029850Z",
-     "start_time": "2019-01-25T20:29:12.983113Z"
+     "end_time": "2019-01-26T15:31:20.693404Z",
+     "start_time": "2019-01-26T15:31:20.642397Z"
     }
    },
    "outputs": [],
@@ -1110,18 +1097,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 24,
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2019-01-25T20:29:13.186720Z",
-     "start_time": "2019-01-25T20:29:13.031320Z"
+     "end_time": "2019-01-26T15:31:34.774506Z",
+     "start_time": "2019-01-26T15:31:34.615290Z"
     }
    },
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "d4e10524d7054a128de4ea96d1523431",
+       "model_id": "06e60e2c64a54f24891470115e01ec01",
        "version_major": 2,
        "version_minor": 0
       },