Merge pull request #20 from MLDERES/dev

Fixing issue #18
MLDERES · Aug 21, 2020 · 93cbff3 · 93cbff3
2 parents ba6bec8 + ce7f75b
commit 93cbff3
Show file tree

Hide file tree

Showing 26 changed files with 769 additions and 138 deletions.
diff --git a/.vscode/settings.json b/.vscode/settings.json
@@ -1,2 +1,8 @@
 {
+    "python.testing.pytestArgs": [
+        "src"
+    ],
+    "python.testing.unittestEnabled": false,
+    "python.testing.nosetestsEnabled": false,
+    "python.testing.pytestEnabled": true
 }
diff --git a/LICENSE b/LICENSE
@@ -0,0 +1,10 @@
+
+The MIT License (MIT)
+Copyright (c) 2020, Michael Dereszynski
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
diff --git a/conf/base/catalog.yml b/conf/base/catalog.yml
@@ -30,7 +30,7 @@ pfr_passing:
   date_range_type : "year"
   start_year : 2019
 
-  pfr_receiving:
+pfr_receiving:
   type: phantasyfootballer.io.CSVRemoteDataSet
   data_source : 'phantasyfootballer.data_providers.pro_fb_ref.fetch_receiving_data'
   date_range_type : "year"
@@ -57,7 +57,7 @@ cbs_projections_remote:
   local_filepath: data/01_raw/cbs_sports_projection.csv
 
 
-fp_projections:
+fp_projections_local:
   <<: *csv
   filepath: data/01_raw/fantasy_pros_projection.csv
   #versioned: True
@@ -72,6 +72,23 @@ projections:
   filepath: data/02_intermediate/projections.csv
   #versioned: True
 
+scoring.ppr:
+  <<: *csv
+  filepath: data/03_primary/scoring_ppr.csv
+
+scoring.half_ppr:
+  <<: *csv
+  filepath: data/03_primary/scoring_half_ppr.csv
+
+scoring.standard:
+  <<: *csv
+  filepath: data/03_primary/scoring_std.csv
+
+scoring_custom:
+  <<: *csv
+  filepath: data/03_primary/scoring_custom.csv
+
+
 
 
 

diff --git a/conf/base/pipelines/data_engineering/catalog.yml b/conf/base/pipelines/data_engineering/catalog.yml
@@ -0,0 +1,5 @@
+# This is a boilerplate catalog config generated for pipeline 'data_engineering'
+# using Kedro 0.16.4.
+#
+# Documentation for this file format can be found in "The Data Catalog"
+# Link: https://kedro.readthedocs.io/en/stable/04_user_guide/04_data_catalog.html
diff --git a/conf/base/pipelines/data_engineering/parameters.yml b/conf/base/pipelines/data_engineering/parameters.yml
@@ -0,0 +1,5 @@
+# This is a boilerplate parameters config generated for pipeline 'data_engineering'
+# using Kedro 0.16.4.
+#
+# Documentation for this file format can be found in
+# https://kedro.readthedocs.io/en/stable/04_user_guide/03_configuration.html#parameters
diff --git a/conf/base/scoring.yml b/conf/base/scoring.yml
@@ -38,4 +38,6 @@ full_ppr:
 half_ppr:
     <<: *standard_scoring
     rcv_rec: 0.5
-
+
+custom:
+    <<: *standard_scoring
diff --git a/notebooks/analysis.ipynb b/notebooks/analysis.ipynb
@@ -24,8 +24,7 @@
     "proj_path = current_dir.parent  # point back to the root of the project\n",
     "context = load_context(proj_path)\n",
     "catalog = context.catalog\n",
-    "\n",
-    "from phantasyfootballer.settings import *"
+    "\n"
    ]
   },
   {
@@ -36,7 +35,10 @@
    },
    "outputs": [],
    "source": [
-    "df_proj = catalog.load('projections')"
+    "from phantasyfootballer.settings import *\n",
+    "from phantasyfootballer.common import Stats\n",
+    "df_ppr = catalog.load('scoring.ppr')\n",
+    "\n"
    ]
   },
   {
@@ -45,19 +47,43 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "stat_columns = ['pass_att', 'pass_comp',\n",
-    "       'pass_int', 'pass_tds', 'pass_yds', 'rcv_rec', 'rcv_tds', 'rcv_yds',\n",
-    "       'rush_att', 'rush_yds', 'rush_tds', 'fumble_lost']\n",
-    "point_columns = ['standard_pts','full_ppr_pts', 'half_ppr_pts']\n",
-    "rank_columns = ['standard_rank', 'full_ppr_rank','half_ppr_rank']\n",
+    "df_ppr.sort_values(Stats.POS_RANK)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
     "\n",
+    "df_ppr[Stats.POS_RANK] = df_ppr.groupby(POSITION)[Stats.FANTASY_POINTS].rank(na_option=\"bottom\", ascending=False)\n",
+    "df_ppr.sort_values(Stats.POS_RANK, ascending=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
     "class projections():\n",
     "\n",
     "    def __init__(self, data):\n",
     "        self._data = data\n",
+    "        self._support_stats = set(Stats.ALL_STATS).intersection(data.columns)\n",
+    "        self._supported_features = None\n",
     "\n",
     "    def stats(self):\n",
-    "        return self._data[stat_columns]\n",
+    "        return self._data[self._support_stats]\n",
+    "\n",
+    "    def pts(self):\n",
+    "        return self._data[[Stats.points('full_ppr'), Stats.points('half_ppr'), Stats.points('standard')]]\n",
+    "    \n",
+    "    def features(self):\n",
+    "        return None\n",
     "\n"
    ]
   },
@@ -68,15 +94,102 @@
    "outputs": [],
    "source": [
     "df_pos_proj = df_proj.groupby(POSITION).mean()\n",
-    "df_pos_proj[stat_columns]\n",
-    "df_proj[rank_columns]"
+    "pos_proj = projections(df_proj)\n",
+    "pos_proj.stats()\n",
+    "pos_proj.pts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pos_proj._data[[Stats.points('full_ppr'), Stats.points('half_ppr'), Stats.points('standard')]]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_full_projections = df_proj.join(df_pos_proj[[Stats.points('full_ppr'), Stats.points('half_ppr'),Stats.points('standard')]], on=POSITION, rsuffix='_apr')\n",
+    "df_full_projections.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def pct_avg_value(df, col):\n",
+    "    df[f'pct_of_avg_{col}'] = df[Stats.points(col)] / df[f'{Stats.points(col)}_apr']\n",
+    "\n",
+    "def pct_median_value(df, col):\n",
+    "    df[f'pct_of_avg_{col}'] = df[Stats.points(col)] / df[f'{Stats.points(col)}_apr']\n",
+    "\n",
+    "\n",
+    "pct_value(df_full_projections,'full_ppr')\n",
+    "pct_value(df_full_projections,'half_ppr')\n",
+    "pct_value(df_full_projections,'standard')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_full_projections.sort_values('pct_of_avg_full_ppr', ascending=False)[[PLAYER_NAME,'pct_of_avg_full_ppr','pct_of_avg_standard','pct_of_avg_half_ppr']]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_full_projections.query('player==\"Travis Kelce\"')\n",
+    "df_pos_proj.loc[TE]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from matplotlib import pyplot as plt \n",
+    "import seaborn as sns\n",
+    "top_rb = df_full_projections.query('position == \"RB\"').sort_values('pct_of_avg_full_ppr',ascending=False)[:36]\n",
+    "top_wr = df_full_projections.query('position == \"WR\"').sort_values('pct_of_avg_full_ppr',ascending=False)[:36]\n",
+    "top_te = df_full_projections.query('position == \"TE\"').sort_values('pct_of_avg_full_ppr',ascending=False)[:36]\n",
+    "top_qb = df_full_projections.query('position == \"QB\"').sort_values('pct_of_avg_full_ppr',ascending=False)[:36]\n",
+    "#.plot(kind='bar',x=PLAYER_NAME,y='pct_of_avg_full_ppr');"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "top_rb.plot(kind='bar',x=PLAYER_NAME,y='pct_of_avg_full_ppr');\n",
+    "top_qb.plot(kind='bar',x=PLAYER_NAME,y='pct_of_avg_full_ppr');\n",
+    "top_wr.plot(kind='bar',x=PLAYER_NAME,y='pct_of_avg_full_ppr');\n",
+    "top_te.plot(kind='bar',x=PLAYER_NAME,y='pct_of_avg_full_ppr');"
    ]
   }
  ],
  "metadata": {
   "kernelspec": {
    "display_name": "Python 3.8.3 64-bit",
-   "name": "python_defaultSpec_1597939435737"
+   "name": "python_defaultSpec_1598024082108"
   },
   "language_info": {
    "codemirror_mode": {

diff --git a/notebooks/sample.ipynb b/notebooks/sample.ipynb
@@ -58,12 +58,72 @@
     "\n",
     "    _calculate_expiration_hours('8H')"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from phantasyfootballer.settings import *\n",
+    "from phantasyfootballer.common import combine_data_horizontal\n",
+    "\n",
+    "df = context.catalog.load('scoring.half_ppr')\n",
+    "df_left = df[KEEPER_COLUMNS]\n",
+    "df_right = df_left.copy()\n",
+    "df_right['NEW_COL'] = 'new_data'\n",
+    "combine_data_horizontal(df_left,df_right)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from phantasyfootballer.settings import *\n",
+    "from phantasyfootballer.common import Stats\n",
+    "data = context.catalog.load('scoring.ppr')\n",
+    "#data.head()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "\n",
+    "\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "pos_data = data.groupby(POSITION)[Stats.FANTASY_POINTS].mean()\n",
+    "joined = data.join(pos_data,on=POSITION,rsuffix='avg')\n",
+    "data[Stats.PCT_AVERAGE] = joined[Stats.FANTASY_POINTS]/joined['fpavg']\n",
+    "joined.head()\n",
+    "data.head()"
+   ]
   }
  ],
  "metadata": {
   "kernelspec": {
    "display_name": "Python 3.8.3 64-bit",
-   "name": "python_defaultSpec_1597939322536"
+   "name": "python_defaultSpec_1598023361223"
   },
   "language_info": {
    "codemirror_mode": {