update notebook

notebooks/factor analysis.ipynb

@@ -41,7 +41,7 @@
     "factor = 'ROEAfterNonRecurring' # 'DROEAfterNonRecurring'\n",
     "\n",
     "conn = sqlalchemy.create_engine('mysql+mysqldb://root:we083826@localhost:3306/multifactor?charset=utf8')\n",
-    "df = pd.read_sql('select factor_data.{0},  trade_data.Return as dailyReturn, {1}.* '\n",
+    "df = pd.read_sql('select factor_data.{0},  trade_data.Return as dailyReturn, {1}.*, 1 as Market '\n",
     "                 'from factor_data, trade_data, {1} '\n",
     "                 'where factor_data.Date = {1}.Date and factor_data.Code = {1}.Code '\n",
     "                 'and factor_data.Date = trade_data.Date and factor_data.Code = trade_data.Code;'.format(factor, \n",
@@ -137,7 +137,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "total_data = df.copy()"
@@ -424,7 +426,7 @@
    "outputs": [],
    "source": [
     "top_sources = aggregated_bars.sum().abs().sort_values(ascending=False).index[:10]\n",
-    "aggregated_bars.sum().abs().sort_values(ascending=False).plot(kind='bar', figsize=(16, 8))"
+    "aggregated_bars.sum().sort_values(ascending=False).plot(kind='bar', figsize=(16, 8))"
    ]
   },
   {
@@ -455,7 +457,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "exposure_table[top_sources[1:]].plot(figsize=(14,7))\n",
+    "exposure_table[top_sources.difference(['idiosyncratic'])].plot(figsize=(14,7))\n",
     "plt.legend(loc='upper center', ncol=len(top_sources[1:]) // 3)"
    ]
   },
@@ -479,62 +481,14 @@
     "del total_data"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": [
-    "total_factors = [factor] + risk_facto_cols.tolist()"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "total_factors"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "aggregated_bars.sum().abs().sort_values(ascending=False)[:10].plot?"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": [
-    "aggregated_bars.sum().abs().sort_values(ascending=False)[:10].plot"
+    "import gc\n",
+    "gc.collect()"
    ]
   },
   {