{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport matplotlib.pyplot as plt\nfrom datetime import datetime\nimport seaborn as sns\n\nimport math","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-11-10T17:06:29.092446Z","iopub.execute_input":"2022-11-10T17:06:29.092898Z","iopub.status.idle":"2022-11-10T17:06:29.099885Z","shell.execute_reply.started":"2022-11-10T17:06:29.092864Z","shell.execute_reply":"2022-11-10T17:06:29.098415Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

Goal of the Competition 🐴

\n

The goal of this competition is to analyze horse racing tactics, drafting strategies, and path efficiency. You will develop a model using never-before-released coordinate data along with basic race information.
\n\nYour work will help racing horse owners, trainers, and veterinarians better understand how equine performance and welfare fit together. With better data analysis, equine welfare could significantly improve.","metadata":{}},{"cell_type":"markdown","source":"

Usefull Funtions

","metadata":{}},{"cell_type":"code","source":"def MemoryOptimisation(DataFrame):\n \n InitialMemory = DataFrame.memory_usage().sum() / 1024 ** 2\n print(f'Initial Memory Usage: \\033[1m{round(InitialMemory, 2)} MB\\033[0m')\n\n SubTypeInt = ['uint8','uint16','uint32','uint64','int8','int16','int32','int64']\n SubTypeFloat = ['float16','float32','float64']\n\n for column in DataFrame.columns:\n\n ColumnType = str(DataFrame[column].dtypes)\n MaximumColumn = DataFrame[column].max()\n MinimumColumn = DataFrame[column].min()\n\n if 'object' in ColumnType:\n NumberOfUnique = len(DataFrame[column].unique())\n NumberOfTotal = len(DataFrame[column])\n if NumberOfUnique / NumberOfTotal < 0.5:\n DataFrame[column] = DataFrame[column].astype('category')\n elif 'int' in ColumnType:\n for element in SubTypeInt:\n if MinimumColumn > np.iinfo(element).min and MaximumColumn < np.iinfo(element).max:\n DataFrame[column] = DataFrame[column].astype(element)\n break\n elif 'float' in ColumnType:\n for element in SubTypeFloat:\n if MinimumColumn > np.finfo(element).min and MaximumColumn < np.finfo(element).max:\n DataFrame[column] = DataFrame[column].astype(element)\n\n FinalMemory = DataFrame.memory_usage().sum() / 1024**2\n print(f'Final Memory Usage after Optimisation: \\033[1m{round(FinalMemory, 2)} MB\\033[0m')\n print(f'Compressed by: \\033[1m{round(100*(InitialMemory - FinalMemory) / InitialMemory, 2)} %\\033[0m')\n return DataFrame\n\n\n# initial Check\n\ndef font_size(s, props=[]):\n color = [\" \" for i in range(len(s))]\n color[0] = props[-1]\n color[-1] = props[-1]\n color[3] = props[-1] \n return color\n\ndef initial_check(df):\n Features = []\n for i in df.columns:\n Features.append([i,df[i].dtype, df[i].nunique(),\n \", \".join([str(i) for i in df[i].drop_duplicates().sort_values().values])])\n display(pd.DataFrame(Features, columns = ['Features','Dtype', 'Unique Count', 'Unique Values']).style\n .set_caption(\"Let's Check All Colums\")\n .format(precision=0)\n .hide_index()\n .apply(font_size, props=[\"font-size: 18px; color:red; border: 2px solid red\",\n \"\"\"display: block;width: 300px;\n text-overflow: ellipsis;\n word-wrap: break-word;\n overflow: hidden;\n max-height: 1.8em;\n line-height: 1.8em;\"\"\" ], axis=1))\n","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T17:00:55.294170Z","iopub.execute_input":"2022-11-10T17:00:55.294639Z","iopub.status.idle":"2022-11-10T17:00:55.312825Z","shell.execute_reply.started":"2022-11-10T17:00:55.294604Z","shell.execute_reply":"2022-11-10T17:00:55.311210Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

Table 1 - Horse/Jockey Race Data

","metadata":{}},{"cell_type":"code","source":"start_table = ['track_id', 'race_date', 'race_number', 'program_number', 'weight_carried', 'jockey', 'odds', 'position_at_finish']\ndateparse = lambda x: datetime.strptime(x, '%Y-%m-%d')\ndf_start = pd.read_csv('../input/big-data-derby-2022/nyra_start_table.csv', names=start_table, parse_dates=['race_date'], date_parser=dateparse)\n# df_start.set_index('race_date', inplace=True)\nprint(f\"\\n\\033[1;30;34m Table have \\033[0;0m \\033[1m{df_start.shape[0]} rows \\033[1;30;34mand\\033[0;0m \\033[1m{df_start.shape[1]} columns\\033[0m \")\ndisplay(df_start.head(2))","metadata":{"execution":{"iopub.status.busy":"2022-11-09T17:45:03.199832Z","iopub.execute_input":"2022-11-09T17:45:03.201336Z","iopub.status.idle":"2022-11-09T17:45:03.426420Z","shell.execute_reply.started":"2022-11-09T17:45:03.201261Z","shell.execute_reply":"2022-11-09T17:45:03.424748Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"initial_check(df_start)","metadata":{"execution":{"iopub.status.busy":"2022-11-09T17:45:07.963014Z","iopub.execute_input":"2022-11-09T17:45:07.963565Z","iopub.status.idle":"2022-11-09T17:45:07.997897Z","shell.execute_reply.started":"2022-11-09T17:45:07.963524Z","shell.execute_reply":"2022-11-09T17:45:07.996163Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"race = df_start.iloc[:, [0,1,2]].drop_duplicates().reset_index(drop=True)\nprint(f\"\\n\\033[1;30;34m Total # Races : \\033[0;0m \\033[1m{race.shape[0]} \\n\")\n\nfig = plt.figure(figsize = (13,3), dpi=100)\ngs = fig.add_gridspec(1,4)\ngs.update(wspace=0.35, hspace=0.47)\nax0 = fig.add_subplot(gs[0,0])\nax1 = fig.add_subplot(gs[0,1])\nax2 = fig.add_subplot(gs[0,2])\nax3 = fig.add_subplot(gs[0,3])\n\na = race.track_id.value_counts().plot(kind='pie', title='# Races by Tracks', autopct='%.0f%%', ax=ax0)\na.set_ylabel(\" \");\n\nc = race.race_date.dt.month.value_counts().sort_index().plot(kind='bar', title='# Races by Month', ax=ax1);\nc.set_xticklabels(['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'])\n\nd = race.race_date.dt.weekday.value_counts().sort_index().plot(kind='bar', title='# Races by Day', ax=ax2);\nd.set_xticklabels(['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', \"Sun\"])\n\ne = race.groupby('race_date').race_number.max().value_counts().sort_index().plot(kind='bar', title=\"Races per Day\", ax=ax3);","metadata":{"execution":{"iopub.status.busy":"2022-11-09T18:31:29.414708Z","iopub.execute_input":"2022-11-09T18:31:29.415173Z","iopub.status.idle":"2022-11-09T18:31:30.149065Z","shell.execute_reply.started":"2022-11-09T18:31:29.415139Z","shell.execute_reply":"2022-11-09T18:31:30.147646Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"β˜… **Total Races :-** `2000`\n\nβ˜… **Racing Track Inference:-** It can be seen that the `825` races were ran at **`AQU - Aqueduct `**, and `772` on **` BEL - Belmont `** and `403` on **` SAR - Saratoga `** at last.\n\nβ˜… **Race Date:-** The majority of the races are scheduled for the **` Fall `**, followed by the **` Summer`**, and **` Winter`**.\n\nβ˜… **Race Day:-** Most of race scheduled on Weekends.\n\nβ˜… **Race per Day:-** Most of time only `9 races` scheduled per day.","metadata":{"execution":{"iopub.status.busy":"2022-11-09T18:09:22.242626Z","iopub.execute_input":"2022-11-09T18:09:22.243096Z","iopub.status.idle":"2022-11-09T18:09:22.253089Z","shell.execute_reply.started":"2022-11-09T18:09:22.243033Z","shell.execute_reply":"2022-11-09T18:09:22.251937Z"}}},{"cell_type":"code","source":"df_start.groupby('jockey').weight_carried.mean().astype(int).value_counts().sort_index()\\\n.plot(kind='bar', title='Avg Weight of Jockey(since large part of weight carried is of jockey)' );","metadata":{"execution":{"iopub.status.busy":"2022-11-09T19:01:28.297146Z","iopub.execute_input":"2022-11-09T19:01:28.297566Z","iopub.status.idle":"2022-11-09T19:01:28.555187Z","shell.execute_reply.started":"2022-11-09T19:01:28.297532Z","shell.execute_reply":"2022-11-09T19:01:28.553985Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\na = sns.relplot(kind='scatter',\n data=df_start.query('odds < 10000'),col_wrap = 5,\n x='weight_carried', y='odds', hue='track_id',\n col='position_at_finish');","metadata":{"execution":{"iopub.status.busy":"2022-11-09T19:07:31.385980Z","iopub.execute_input":"2022-11-09T19:07:31.387007Z","iopub.status.idle":"2022-11-09T19:07:36.685302Z","shell.execute_reply.started":"2022-11-09T19:07:31.386966Z","shell.execute_reply":"2022-11-09T19:07:36.684152Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**ODDS Never Help!!**","metadata":{}},{"cell_type":"markdown","source":"

Table 2 - Racetrack Race Data

","metadata":{}},{"cell_type":"code","source":"df_race = pd.read_csv('../input/big-data-derby-2022/nyra_race_table.csv', parse_dates=['race_date'])\nprint(f\"\\n\\033[1;30;34m Table have \\033[0;0m \\033[1m{df_race.shape[0]} rows \\033[1;30;34mand\\033[0;0m \\033[1m{df_race.shape[1]} columns\\033[0m \")\ndisplay(df_race.head(2))","metadata":{"execution":{"iopub.status.busy":"2022-11-10T17:23:23.673478Z","iopub.execute_input":"2022-11-10T17:23:23.673871Z","iopub.status.idle":"2022-11-10T17:23:23.708494Z","shell.execute_reply.started":"2022-11-10T17:23:23.673839Z","shell.execute_reply":"2022-11-10T17:23:23.706631Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"initial_check(df_race)","metadata":{"execution":{"iopub.status.busy":"2022-11-10T17:01:01.059454Z","iopub.execute_input":"2022-11-10T17:01:01.059943Z","iopub.status.idle":"2022-11-10T17:01:01.149158Z","shell.execute_reply.started":"2022-11-10T17:01:01.059894Z","shell.execute_reply":"2022-11-10T17:01:01.147689Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"
SAR - Saratoga
\n

Saratoga Race Course, situated in Saratoga Spring a city in New York, United States. Famous for thoroughbred horse racing.

\n\n
AQU - Aqueduct
\n

Aqueduct Racetrack is a Thoroughbred horse racing facility in Queens, New York City, United States.

\n\n
BEL - Belmont
\n

The Belmont Stakes is an American Grade I stakes race for three-year-old Thoroughbreds run at Belmont Park in Elmont, New York, United States.

\n\nAll three track are in New York, United States","metadata":{"execution":{"iopub.status.busy":"2022-11-10T18:17:27.432617Z","iopub.execute_input":"2022-11-10T18:17:27.433023Z","iopub.status.idle":"2022-11-10T18:17:27.440551Z","shell.execute_reply.started":"2022-11-10T18:17:27.432991Z","shell.execute_reply":"2022-11-10T18:17:27.439203Z"}}},{"cell_type":"code","source":"df_race['race_month'] = df_race.race_date.dt.month\ndf_race.groupby(['race_month', 'track_id']).size().unstack().plot(kind='bar', stacked=True, title='# Race by Month and Track');\n","metadata":{"execution":{"iopub.status.busy":"2022-11-10T19:04:13.307537Z","iopub.execute_input":"2022-11-10T19:04:13.308323Z","iopub.status.idle":"2022-11-10T19:04:13.663023Z","shell.execute_reply.started":"2022-11-10T19:04:13.308278Z","shell.execute_reply":"2022-11-10T19:04:13.661680Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Race track-** All winter matches held in Aqueduct. August, which register highest number of races, all matches held in Saratoga ","metadata":{}},{"cell_type":"code","source":"# distance_id\nprint('Distance is in furlongs')\nprint('A furlong is a measure of distance in imperial units and United States customary units equal to one\\\n eighth of a mile, equivalent to 660 feet, 220 yards, 40 rods, 10 chains or approximately 201 metres.')\n\ndf_race['distance']=((df_race.distance_id/100)*201//100*100).astype(int)\ndf_race.distance.value_counts().sort_index().plot(kind='bar', title='Distance(Meter) of the Race');","metadata":{"execution":{"iopub.status.busy":"2022-11-10T17:33:04.694655Z","iopub.execute_input":"2022-11-10T17:33:04.696253Z","iopub.status.idle":"2022-11-10T17:33:05.013386Z","shell.execute_reply.started":"2022-11-10T17:33:04.696192Z","shell.execute_reply":"2022-11-10T17:33:05.011900Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"β˜… **Distance of the race:-** More than `500+ races` are of distance `1200 meters`.","metadata":{}},{"cell_type":"code","source":"df_race['course_type']=df_race.course_type.replace({'M': 'Hurdle', 'D' :'Dirt', 'O' : 'Outer Turf', 'I' : 'Inner Turf', 'T' : 'Turf'})\n\n\nfig = plt.figure(figsize = (13,8), dpi=100)\ngs = fig.add_gridspec(2,2)\ngs.update(wspace=0.35, hspace=0.6)\nax0 = fig.add_subplot(gs[0,0])\nax1 = fig.add_subplot(gs[0,1])\nax2 = fig.add_subplot(gs[1,0])\n\n\na = df_race.groupby(['course_type', 'track_id']).size().unstack().plot(kind='bar', stacked=True, title='# Race by Course Type', ax=ax0);\na.set_xlabel('')\n\ndf_race.groupby(['race_month', 'course_type']).size().unstack().plot(kind='bar', stacked=True, title='# Race by Month and Course type', ax=ax1);\n\ndf_race.groupby(['distance','course_type']).size().unstack().plot(kind='bar', stacked=True, ax=ax2)","metadata":{"execution":{"iopub.status.busy":"2022-11-10T18:59:28.110005Z","iopub.execute_input":"2022-11-10T18:59:28.110530Z","iopub.status.idle":"2022-11-10T18:59:29.408806Z","shell.execute_reply.started":"2022-11-10T18:59:28.110490Z","shell.execute_reply":"2022-11-10T18:59:29.407276Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"β˜… **Course Type :-** More than `70%` of Race are in `Dirt`.\n\nβ˜… Turf is simply Grass. Since grass is a living and growing plant, turf racing is seasonal. In New York, for example, turf racing isn’t conducted during the winter. ","metadata":{}},{"cell_type":"code","source":"a = sns.relplot(kind='scatter', height=2.5,\n data=df_race,col_wrap = 3,\n x='distance_id', y='purse',\n col='course_type'\n );","metadata":{"execution":{"iopub.status.busy":"2022-11-10T17:00:58.752126Z","iopub.execute_input":"2022-11-10T17:00:58.752572Z","iopub.status.idle":"2022-11-10T17:00:59.823085Z","shell.execute_reply.started":"2022-11-10T17:00:58.752534Z","shell.execute_reply":"2022-11-10T17:00:59.822127Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

To Be Continued....","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}