finished some jrnl analysis, not sure what more to do other than NLP stuff maybe

README.md

@@ -6,7 +6,7 @@ data from:
 
 * Web browser
 * Loop Habits
-* * Nextcloud backup
+* * Nextcloud backup -> rename 'Date' to 'date'
 * Taskwarrior
 * * Run 'task export'
 * Wallabag

notebook.ipynb

@@ -17,6 +17,151 @@
     "    return df.filter(like='2019', axis=0)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Shaarli"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#  Journal"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### make a journal_fixer script \n",
+    "\n",
+    "### import journal into habits data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "According to habits I have 49 Journal entries\n",
+    "\n",
+    "\n",
+    "Let's compare that with this data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 106,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "tags     87\n",
+       "text     88\n",
+       "title    88\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 106,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "with open('data/tiddlers.json' , 'r') as file:\n",
+    "    tiddly = json.load(file)\n",
+    "\n",
+    "jrnl = pd.DataFrame.from_dict(tiddly)\n",
+    "jrnl.set_axis(jrnl['title'], axis='index', inplace=True)\n",
+    "jrnl = only2019(jrnl.drop(['created', 'modified'], axis=1))\n",
+    "jrnl.count()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 107,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "tags     30\n",
+       "text     30\n",
+       "title    30\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 107,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sameDay = jrnl\n",
+    "sameDay['title'] = sameDay.title.map(lambda x: x[:-8])\n",
+    "sameDay[sameDay['title'].duplicated(keep=False)].count()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Where are the [87-15=(73)] - 49 = 23 entries that exist but aren't in my loop Habits?\n",
+    "\n",
+    "23 Entries before March?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 119,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def beforeMarch(df):\n",
+    "    return df.filter(regex='(January|Febuary|March)', axis=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 121,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "tags     23\n",
+       "text     23\n",
+       "title    23\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 121,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "beforeMarch(jrnl).count()"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -185,6 +330,16 @@
     "    print(\"  \" + e)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Most described task?\n",
+    "## TODO"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -194,7 +349,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 69,
+   "execution_count": 100,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -206,7 +361,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 183,
+   "execution_count": 105,
    "metadata": {},
    "outputs": [
     {
@@ -404,14 +559,14 @@
        "12     0.387097  0.548387  1.096774  0.709677  0.612903  0.000000  0.612903"
       ]
      },
-     "execution_count": 183,
+     "execution_count": 105,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "#colNames = ['date', 'Godmode', 'Meditate', 'Exercise', 'Piano','Read', 'Journal', 'Gratitude', 'devlog','Plants', 'Job', 'Draw']\n",
-    "checks = pd.read_csv('LoopHabits/Checkmarks.csv', header=0)\n",
+    "checks = pd.read_csv('data/LoopHabits/Checkmarks.csv', header=0)\n",
     "checks.set_axis(checks['date'], axis='index', inplace=True)\n",
     "checks = checks.drop(['Godmode', 'Piano', 'Gratitude', 'Job', 'date'], axis=1)\n",
     "df = MarchOnwards(only2019(checks))\n",
@@ -429,7 +584,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 69,
+   "execution_count": 102,
    "metadata": {},
    "outputs": [],
    "source": [