fix analysis bug

docs/component/report.rst

@@ -108,35 +108,35 @@ Graphical Result
 .. image:: ../_static/img/analysis/score_ic.png 
 
 
-Usage of `analysis_position.cumulative_return`
+.. Usage of `analysis_position.cumulative_return`
-----------------------------------------------
+.. ----------------------------------------------
-
+..
-API
+.. API
-~~~~~~~~~~~~~~~~
+.. ~~~~~~~~~~~~~~~~
-
+..
-.. automodule:: qlib.contrib.report.analysis_position.cumulative_return
+.. .. automodule:: qlib.contrib.report.analysis_position.cumulative_return
-    :members:
+..     :members:
-
+..
-Graphical Result
+.. Graphical Result
-~~~~~~~~~~~~~~~~~
+.. ~~~~~~~~~~~~~~~~~
-
+..
-.. note:: 
+.. .. note:: 
-
+..
-    - Axis X: Trading day
+..     - Axis X: Trading day
-    - Axis Y:
+..     - Axis Y:
-        - Above axis Y: `(((Ref($close, -1)/$close - 1) * weight).sum() / weight.sum()).cumsum()`
+..         - Above axis Y: `(((Ref($close, -1)/$close - 1) * weight).sum() / weight.sum()).cumsum()`
-        - Below axis Y: Daily weight sum
+..         - Below axis Y: Daily weight sum
-    - In the **sell** graph, `y < 0` stands for profit; in other cases, `y > 0` stands for profit.
+..     - In the **sell** graph, `y < 0` stands for profit; in other cases, `y > 0` stands for profit.
-    - In the **buy_minus_sell** graph, the **y** value of the **weight** graph at the bottom is `buy_weight + sell_weight`.
+..     - In the **buy_minus_sell** graph, the **y** value of the **weight** graph at the bottom is `buy_weight + sell_weight`.
-    - In each graph, the **red line** in the histogram on the right represents the average.                                                                                                        
+..     - In each graph, the **red line** in the histogram on the right represents the average.
-
+..
-.. image:: ../_static/img/analysis/cumulative_return_buy.png 
+.. .. image:: ../_static/img/analysis/cumulative_return_buy.png 
-
+..
-.. image:: ../_static/img/analysis/cumulative_return_sell.png 
+.. .. image:: ../_static/img/analysis/cumulative_return_sell.png 
-
+..
-.. image:: ../_static/img/analysis/cumulative_return_buy_minus_sell.png 
+.. .. image:: ../_static/img/analysis/cumulative_return_buy_minus_sell.png 
-
+..
-.. image:: ../_static/img/analysis/cumulative_return_hold.png 
+.. .. image:: ../_static/img/analysis/cumulative_return_hold.png 
 
 
 Usage of `analysis_position.risk_analysis`
@@ -220,42 +220,42 @@ Graphical Result
 .. image:: ../_static/img/analysis/risk_analysis_std.png 
     :align: center
 
-
+..
-Usage of `analysis_position.rank_label`
+.. Usage of `analysis_position.rank_label`
-----------------------------------------------
+.. ----------------------------------------------
-
+..
-API
+.. API
-~~~~~
+.. ~~~~~
-
+..
-.. automodule:: qlib.contrib.report.analysis_position.rank_label
+.. .. automodule:: qlib.contrib.report.analysis_position.rank_label
-    :members:
+..     :members:
-
+..
-
+..
-Graphical Result
+.. Graphical Result
-~~~~~~~~~~~~~~~~~
+.. ~~~~~~~~~~~~~~~~~
-
+..
-.. note:: 
+.. .. note:: 
-
+..
-    - hold/sell/buy graphics:
+..     - hold/sell/buy graphics:
-        - Axis X: Trading day
+..         - Axis X: Trading day
-        - Axis Y: 
+..         - Axis Y: 
-            Average `ranking ratio`of `label` for stocks that is held/sold/bought on the trading day.
+..             Average `ranking ratio`of `label` for stocks that is held/sold/bought on the trading day.
-
+..
-            In the above example, the `label` is formulated as `Ref($close, -1)/$close - 1`. The `ranking ratio` can be formulated as follows.
+..             In the above example, the `label` is formulated as `Ref($close, -1)/$close - 1`. The `ranking ratio` can be formulated as follows.
-            .. math::
+..             .. math::
-                
+..                 
-                ranking\ ratio = \frac{Ascending\ Ranking\ of\ label}{Number\ of\ Stocks\ in\ the\ Portfolio}
+..                 ranking\ ratio = \frac{Ascending\ Ranking\ of\ label}{Number\ of\ Stocks\ in\ the\ Portfolio}
-
+..
-.. image:: ../_static/img/analysis/rank_label_hold.png 
+.. .. image:: ../_static/img/analysis/rank_label_hold.png 
-    :align: center
+..     :align: center
-
+..
-.. image:: ../_static/img/analysis/rank_label_buy.png 
+.. .. image:: ../_static/img/analysis/rank_label_buy.png 
-    :align: center
+..     :align: center
-
+..
-.. image:: ../_static/img/analysis/rank_label_sell.png 
+.. .. image:: ../_static/img/analysis/rank_label_sell.png 
-    :align: center
+..     :align: center
-
+..
-
+..
 
 Usage of `analysis_model.analysis_model_performance`
 -----------------------------------------------------

examples/estimator/analyze_from_estimator.ipynb

@@ -80,25 +80,6 @@
     "positions = pickle.load(estimator_dir.joinpath('positions.pkl').open('rb'))"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# get label data from qlib"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from qlib.data import D\n",
-    "pred_df_dates = pred_df.index.get_level_values(level='datetime')\n",
-    "features_df = D.features(D.instruments(MARKET), ['Ref($close, -1)/$close - 1'], pred_df_dates.min(), pred_df_dates.max())\n",
-    "features_df.columns = ['label']"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -112,7 +93,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from qlib.contrib.report import analysis_model, analysis_position"
+    "from qlib.data import D\n",
+    "from qlib.contrib.report import analysis_model, analysis_position\n",
+    "pred_df_dates = pred_df.index.get_level_values(level='datetime')"
    ]
   },
   {
@@ -122,6 +105,16 @@
     "## analysis position"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "stock_ret = D.features(D.instruments(MARKET), ['Ref($close, -1)/$close - 1'], pred_df_dates.min(), pred_df_dates.max())\n",
+    "stock_ret.columns = ['label']"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -138,41 +131,6 @@
     "analysis_position.report_graph(report_normal_df)"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### score IC"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "pred_label = pd.concat([features_df, pred_df], axis=1, sort=True).reindex(features_df.index)\n",
-    "analysis_position.score_ic_graph(pred_label)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### cumulative return"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "scrolled": false
-   },
-   "outputs": [],
-   "source": [
-    "analysis_position.cumulative_return_graph(positions, report_normal_df, features_df)"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -183,9 +141,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
+   "metadata": {},
-    "scrolled": false
-   },
    "outputs": [],
    "source": [
     "analysis_position.risk_analysis_graph(analysis_df, report_normal_df)"
@@ -195,7 +151,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### rank label"
+    "## analysis model"
    ]
   },
   {
@@ -204,14 +160,25 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "analysis_position.rank_label_graph(positions, features_df, pred_df_dates.min(), pred_df_dates.max())"
+    "label_df = D.features(D.instruments(MARKET), ['Ref($close, -2)/Ref($close, -1) - 1'], pred_df_dates.min(), pred_df_dates.max())\n",
+    "label_df.columns = ['label']"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## analysis model"
+    "### score IC"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pred_label = pd.concat([label_df, pred_df], axis=1, sort=True).reindex(label_df.index)\n",
+    "analysis_position.score_ic_graph(pred_label)"
    ]
   },
   {
@@ -224,9 +191,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
+   "metadata": {},
-    "scrolled": false
-   },
    "outputs": [],
    "source": [
     "analysis_model.model_performance_graph(pred_label)"

examples/train_backtest_analyze.ipynb

@@ -62,7 +62,6 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {
-    "scrolled": true,
     "tags": []
    },
    "outputs": [],
@@ -195,7 +194,19 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from qlib.contrib.report import analysis_model, analysis_position"
+    "from qlib.contrib.report import analysis_model, analysis_position\n",
+    "from qlib.data import D\n",
+    "pred_df_dates = pred_score.index.get_level_values(level='datetime')\n",
+    "report_normal_df = report_normal\n",
+    "positions = positions_normal\n",
+    "pred_df = pred_score"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## analysis position"
    ]
   },
   {
@@ -204,18 +215,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# get label data\n",
+    "stock_ret = D.features(D.instruments(MARKET), ['Ref($close, -1)/$close - 1'], pred_df_dates.min(), pred_df_dates.max())\n",
-    "from qlib.data import D\n",
+    "stock_ret.columns = ['label']"
-    "pred_df_dates = pred_score.index.get_level_values(level='datetime')\n",
-    "features_df = D.features(D.instruments(MARKET), ['Ref($close, -1)/$close - 1'], pred_df_dates.min(), pred_df_dates.max())\n",
-    "features_df.columns = ['label']"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## analysis position"
    ]
   },
   {
@@ -231,7 +232,40 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "analysis_position.report_graph(report_normal)"
+    "analysis_position.report_graph(report_normal_df)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### risk analysis"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "analysis_position.risk_analysis_graph(analysis_df, report_normal_df)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## analysis model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "label_df = D.features(D.instruments(MARKET), ['Ref($close, -2)/Ref($close, -1) - 1'], pred_df_dates.min(), pred_df_dates.max())\n",
+    "label_df.columns = ['label']"
    ]
   },
   {
@@ -247,69 +281,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "pred_label = pd.concat([features_df, pred_score], axis=1, sort=True).reindex(features_df.index)\n",
+    "pred_label = pd.concat([label_df, pred_df], axis=1, sort=True).reindex(label_df.index)\n",
     "analysis_position.score_ic_graph(pred_label)"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### cumulative return"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "scrolled": false
-   },
-   "outputs": [],
-   "source": [
-    "analysis_position.cumulative_return_graph(positions_normal, report_normal, features_df)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### risk analysis"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "scrolled": false
-   },
-   "outputs": [],
-   "source": [
-    "analysis_position.risk_analysis_graph(analysis_df, report_normal)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### rank label"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "analysis_position.rank_label_graph(positions_normal, features_df, pred_df_dates.min(), pred_df_dates.max())"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## analysis model"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -320,9 +295,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
+   "metadata": {},
-    "scrolled": false
-   },
    "outputs": [],
    "source": [
     "analysis_model.model_performance_graph(pred_label)"
@@ -344,8 +317,7 @@
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
+   "pygments_lexer": "ipython3"
-   "version": "3.8.5"
   },
   "toc": {
    "base_numbering": 1,

qlib/__init__.py

@@ -2,7 +2,7 @@
 # Licensed under the MIT License.
 
 
-__version__ = "0.5.0"
+__version__ = "0.5.0.dev"
 
 import os
 import copy

qlib/contrib/report/analysis_model/analysis_model_performance.py

@@ -264,17 +264,18 @@ def model_performance_graph(
 ) -> [list, tuple]:
     """Model performance
 
-    :param pred_label: index is **pd.MultiIndex**, index name is **[instrument, datetime]**; columns names is **[score, label]**
+    :param pred_label: index is **pd.MultiIndex**, index name is **[instrument, datetime]**; columns names is **[score,
+    label]**. It is usually same as the label of model training(e.g. "Ref($close, -2)/Ref($close, -1) - 1")
 
 
             .. code-block:: python
 
                 instrument	datetime        score       label
                 SH600004	2017-12-11	-0.013502       -0.013502
-                            2017-12-12	-0.072367       -0.072367
+                                2017-12-12	-0.072367       -0.072367
-                            2017-12-13	-0.068605       -0.068605
+                                2017-12-13	-0.068605       -0.068605
-                            2017-12-14	0.012440        0.012440
+                                2017-12-14	0.012440        0.012440
-                            2017-12-15	-0.102778       -0.102778
+                                2017-12-15	-0.102778       -0.102778
 
 
     :param lag: `pred.groupby(level='instrument')['score'].shift(lag)`. It will be only used in the auto-correlation computing.

setup.py

@@ -12,7 +12,7 @@ from setuptools import find_packages, setup, Extension
 NAME = "qlib"
 DESCRIPTION = "A Quantitative-research Platform"
 REQUIRES_PYTHON = ">=3.5.0"
-VERSION = "0.5.0"
+VERSION = "0.5.0.dev"
 
 # Detect Cython
 try: