{"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":"markdown","source":"
\nBOJAHC: Building Optimal Jockey And Horse Combos","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19"}},{"cell_type":"markdown","source":"![news-NYRA.jpg](attachment:fffd9c79-ea73-431f-979e-f8ab138f1d85.jpg)![news-nytha-logo.png](attachment:6c43a4e5-cd15-4fdc-839b-ad409607c5c9.png)","metadata":{},"attachments":{"fffd9c79-ea73-431f-979e-f8ab138f1d85.jpg":{"image/jpeg":"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"},"6c43a4e5-cd15-4fdc-839b-ad409607c5c9.png":{"image/png":"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"}}},{"cell_type":"markdown","source":"# 1. Introduction and Key Results","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\n\nimport plotly.express as px\nimport plotly.graph_objects as go\n\nfrom itertools import product\n\nimport gc\n\nfrom IPython.core.display import display, HTML\nimport plotly","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:27:26.822649Z","iopub.execute_input":"2022-11-10T19:27:26.823182Z","iopub.status.idle":"2022-11-10T19:27:28.338498Z","shell.execute_reply.started":"2022-11-10T19:27:26.823079Z","shell.execute_reply":"2022-11-10T19:27:28.337420Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"id_maps = {\n \"track_id\": {\n \"AQU\": \"Aqueduct\",\n \"BEL\": \"Belmont\",\n \"SAR\": \"Saratoga\"\n },\n \"course_type\": {\n \"M\": \"Hurdle\",\n \"D\": \"Dirt\",\n \"O\": \"Outer Turf\",\n \"I\": \"Inner Turf\",\n \"T\": \"Turf\"\n },\n \"track_condition\": {\n \"YL \": \"Yielding\",\n \"FM \": \"Firm\",\n \"SY \": \"Sloppy\",\n \"GD \": \"Good\",\n \"FT \": \"Fast\",\n \"MY \": \"Muddy\",\n \"SF \": \"Soft\"\n },\n \"race_type\": {\n \"STK\": \"Stakes\",\n \"WCL\": \"Waiver Claiming\",\n \"WMC\": \"Waiver Maiden Claiming\",\n \"SST\": \"Starter Stakes\",\n \"SHP\": \"Starter Handicap\",\n \"CLM\": \"Claiming\",\n \"STR\": \"Starter Allowance\",\n \"AOC\": \"Allowance Optionl Claimer\",\n \"SOC\": \"Starter Optional Claimer\",\n \"MCL\": \"Maiden Claiming\",\n \"ALW\": \"Allowance\",\n \"MSW\": \"Maiden Special Weight\"\n }\n}","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:27:28.340169Z","iopub.execute_input":"2022-11-10T19:27:28.340832Z","iopub.status.idle":"2022-11-10T19:27:28.348856Z","shell.execute_reply.started":"2022-11-10T19:27:28.340791Z","shell.execute_reply":"2022-11-10T19:27:28.347491Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"columns = [\n \"track_id\",\n \"race_date\",\n \"race_number\",\n \"program_number\",\n \"trakus_index\",\n \"latitude\",\n \"longitude\",\n \"distance_id\",\n \"course_type\",\n \"track_condition\",\n \"run_up_distance\",\n \"race_type\",\n \"post_time\",\n \"purse\", # ?\n \"weight_carried\",\n \"jockey\",\n \"odds\",\n \"position_at_finish\"\n ]\n\ncolumn_dtypes = {\n \"track_id\": str,\n \"race_date\": str,\n \"race_number\": str,\n \"program_number\": str,\n \"trakus_index\": int,\n \"latitude\": float,\n \"longitude\": float,\n \"distance_id\": int,\n \"course_type\": str,\n \"track_condition\": str,\n \"run_up_distance\": int,\n \"race_type\": str,\n \"post_time\": str,\n \"purse\": int, # ?\n \"weight_carried\": int,\n \"jockey\": str,\n \"odds\": int,\n \"position_at_finish\": int\n }","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:27:28.350267Z","iopub.execute_input":"2022-11-10T19:27:28.350627Z","iopub.status.idle":"2022-11-10T19:27:28.362334Z","shell.execute_reply.started":"2022-11-10T19:27:28.350597Z","shell.execute_reply":"2022-11-10T19:27:28.360892Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\ndf = pd.read_csv('../input/big-data-derby-2022/nyra_2019_complete.csv', header=0, names=columns, index_col=False)","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2022-11-10T19:27:28.364919Z","iopub.execute_input":"2022-11-10T19:27:28.365313Z","iopub.status.idle":"2022-11-10T19:27:45.415292Z","shell.execute_reply.started":"2022-11-10T19:27:28.365265Z","shell.execute_reply":"2022-11-10T19:27:45.413746Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def preprocess(df, winners=True):\n # sort by: 'track_id', 'race_date', 'race_number', 'trakus_index'\n df = df.sort_values(by=['track_id', 'race_date', 'race_number', 'trakus_index'])\n \n # there are 2000 races in the dataset\n df['race_id'] = df.groupby(['track_id', 'race_date', 'race_number']).ngroup()\n \n # select winners\n if winners:\n df = df.loc[df['position_at_finish'] == 1]\n # select last place\n else:\n df_contestants = pd.DataFrame(df.groupby('race_id')['position_at_finish'].max().rename('contestants'))\n df = pd.merge(df, df_contestants, on='race_id')\n df = df.loc[df['position_at_finish'] == df['contestants']]\n df = df.drop(columns='contestants')\n \n # turns out that there are 2023 program and jockeys who finished first.\n # that's more than the number of races. Is this due to ties?\n racer_groups = df.groupby(['track_id', 'race_date', 'race_number', 'program_number', 'jockey'])\n df['racer_id'] = racer_groups.ngroup()\n \n # this will be our key support data point on which we'll aggregate paths, velocities and accelerations\n df['racer_instant'] = racer_groups.cumcount()\n \n # to calculate distance: prev_lat, prev_long. \n df['prev_lat'] = racer_groups.shift(1)['latitude']\n df['prev_lon'] = racer_groups.shift(1)['longitude']\n \n # convert lat and lon distances to km distances (according to simple formula)\n df['dist_x'] = (df['longitude'] - df['prev_lon']) * np.cos(df['latitude'] / 180 * np.pi) * 40075 / 360\n df['dist_y'] = (df['latitude'] - df['prev_lat']) * 40075 / 360\n df['distance'] = np.sqrt(df['dist_x']**2 + df['dist_y']**2)\n \n # velocity [km / h]\n df['vel_x'] = df['dist_x'] / 0.25 * 3600\n df['vel_y'] = df['dist_y'] / 0.25 * 3600\n df['velocity'] = np.sqrt(df['vel_x']**2 + df['vel_y']**2)\n \n # to calculate acceleration: prev_vel.\n df['prev_vel_x'] = df.groupby('racer_id').shift(1)['vel_x']\n df['prev_vel_y'] = df.groupby('racer_id').shift(1)['vel_y']\n \n # acceleration [m / s**2]\n df['acc_x'] = (df['vel_x'] - df['prev_vel_x']) / 0.25 / 1000\n df['acc_y'] = (df['vel_y'] - df['prev_vel_y']) / 0.25 / 1000\n df['acceleration'] = np.sqrt(df['acc_x']**2 + df['acc_y']**2)\n \n # There are some outliers in velocity.\n # Also, it seems that the trakus_index refresh rate \"hiccups\" once in a while,\n # as in it seems that it doesn't collect data exactly every 0.25 seconds.\n # It happense very rarely though, so for our purposes, since we're taking averages,\n # we'll filter rows where velocity > 100km/h\n df = df.loc[df['velocity'] <= 100]\n df = df.loc[np.absolute(df['prev_vel_x']) <= 100]\n df = df.loc[np.absolute(df['prev_vel_y']) <= 100]\n \n # calculate seconds from trakus_index\n df['seconds'] = df['trakus_index'] * 0.25\n \n # create bins for rup up distance\n near = 5\n df['run_up_distance_bins'] = ((df['run_up_distance'] / near).round() * near)\n df['run_up_distance_bins'] = df['run_up_distance_bins'].map(lambda x: f\"{max(0.0, x-near/2):.1f}-{x+near/2:.1f}\")\n \n return df","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:27:45.417581Z","iopub.execute_input":"2022-11-10T19:27:45.418559Z","iopub.status.idle":"2022-11-10T19:27:45.438041Z","shell.execute_reply.started":"2022-11-10T19:27:45.418508Z","shell.execute_reply":"2022-11-10T19:27:45.437007Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\ndf = preprocess(df, winners=True)\ngc.collect()","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2022-11-10T19:27:45.439487Z","iopub.execute_input":"2022-11-10T19:27:45.439922Z","iopub.status.idle":"2022-11-10T19:27:54.599874Z","shell.execute_reply.started":"2022-11-10T19:27:45.439880Z","shell.execute_reply":"2022-11-10T19:27:54.598778Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"racer_df = df.groupby('racer_id')[[\n 'race_id',\n 'track_id', \n 'race_date', \n 'race_number', \n 'race_type',\n 'program_number', \n 'distance_id', \n 'course_type', \n 'track_condition', \n 'run_up_distance_bins'\n]].first().reset_index(level=0)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:27:54.603297Z","iopub.execute_input":"2022-11-10T19:27:54.604328Z","iopub.status.idle":"2022-11-10T19:27:55.013841Z","shell.execute_reply.started":"2022-11-10T19:27:54.604290Z","shell.execute_reply":"2022-11-10T19:27:55.012526Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_counts_by_col(df, col, threshold=50):\n counts = df.groupby('race_id')[col].first().value_counts()\n counts = counts[counts > threshold]\n vals = list(counts.index)\n return counts, vals","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:27:55.015744Z","iopub.execute_input":"2022-11-10T19:27:55.016239Z","iopub.status.idle":"2022-11-10T19:27:55.023514Z","shell.execute_reply.started":"2022-11-10T19:27:55.016196Z","shell.execute_reply":"2022-11-10T19:27:55.022282Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"col_unique_values = {}","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:27:55.025231Z","iopub.execute_input":"2022-11-10T19:27:55.025614Z","iopub.status.idle":"2022-11-10T19:27:55.035694Z","shell.execute_reply.started":"2022-11-10T19:27:55.025555Z","shell.execute_reply":"2022-11-10T19:27:55.034383Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"track_id_counts, col_unique_values['track_id'] = get_counts_by_col(df, 'track_id')\ntrack_id_counts","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2022-11-10T19:27:55.039531Z","iopub.execute_input":"2022-11-10T19:27:55.039965Z","iopub.status.idle":"2022-11-10T19:27:55.088251Z","shell.execute_reply.started":"2022-11-10T19:27:55.039908Z","shell.execute_reply":"2022-11-10T19:27:55.087011Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"track_condition_counts, col_unique_values['track_condition'] = get_counts_by_col(df, 'track_condition')\ntrack_condition_counts","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2022-11-10T19:27:55.089927Z","iopub.execute_input":"2022-11-10T19:27:55.091244Z","iopub.status.idle":"2022-11-10T19:27:55.150876Z","shell.execute_reply.started":"2022-11-10T19:27:55.091194Z","shell.execute_reply":"2022-11-10T19:27:55.149725Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"course_type_counts, col_unique_values['course_type'] = get_counts_by_col(df, 'course_type')\ncourse_type_counts","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2022-11-10T19:27:55.152479Z","iopub.execute_input":"2022-11-10T19:27:55.152845Z","iopub.status.idle":"2022-11-10T19:27:55.204806Z","shell.execute_reply.started":"2022-11-10T19:27:55.152800Z","shell.execute_reply":"2022-11-10T19:27:55.203533Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"race_type_counts, col_unique_values['race_type'] = get_counts_by_col(df, 'race_type')\nrace_type_counts","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2022-11-10T19:27:55.206296Z","iopub.execute_input":"2022-11-10T19:27:55.206928Z","iopub.status.idle":"2022-11-10T19:27:55.251710Z","shell.execute_reply.started":"2022-11-10T19:27:55.206887Z","shell.execute_reply":"2022-11-10T19:27:55.250411Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"distance_id_counts, col_unique_values['distance_id'] = get_counts_by_col(df, 'distance_id')\ndistance_id_counts","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2022-11-10T19:27:55.253290Z","iopub.execute_input":"2022-11-10T19:27:55.253657Z","iopub.status.idle":"2022-11-10T19:27:55.277517Z","shell.execute_reply.started":"2022-11-10T19:27:55.253628Z","shell.execute_reply":"2022-11-10T19:27:55.276405Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"run_up_distance_bins_counts, col_unique_values['run_up_distance_bins'] = get_counts_by_col(df, 'run_up_distance_bins')\nrun_up_distance_bins_counts","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2022-11-10T19:27:55.278653Z","iopub.execute_input":"2022-11-10T19:27:55.278967Z","iopub.status.idle":"2022-11-10T19:27:55.325027Z","shell.execute_reply.started":"2022-11-10T19:27:55.278927Z","shell.execute_reply":"2022-11-10T19:27:55.323860Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"col_unique_values","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2022-11-10T19:27:55.326489Z","iopub.execute_input":"2022-11-10T19:27:55.326954Z","iopub.status.idle":"2022-11-10T19:27:55.334420Z","shell.execute_reply.started":"2022-11-10T19:27:55.326904Z","shell.execute_reply":"2022-11-10T19:27:55.333502Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_categories_with_threshold(col_unique_values, threshold=12):\n values = list(col_unique_values.values())\n cols = col_unique_values.keys()\n category_dfs = []\n combos = list(product(*values))\n print(len(combos))\n for category in combos:\n cat_dict = {key: val for key, val in zip(cols, category)}\n query_string = ' and '.join(\n f'({key} == \"{val}\")' if type(val) == str else f'({key} == {val})' \n for key, val in cat_dict.items()\n )\n race_count = racer_df.query(query_string).shape[0]\n if race_count < threshold:\n continue\n category_df = df.query(query_string)\n category_dfs.append(\n {\n \"category\": cat_dict,\n \"races\": race_count,\n \"df\": category_df\n }\n )\n \n return category_dfs","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:27:55.335535Z","iopub.execute_input":"2022-11-10T19:27:55.335912Z","iopub.status.idle":"2022-11-10T19:27:55.348247Z","shell.execute_reply.started":"2022-11-10T19:27:55.335873Z","shell.execute_reply":"2022-11-10T19:27:55.347009Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\ncategory_dfs = get_categories_with_threshold(col_unique_values)","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2022-11-10T19:27:55.349972Z","iopub.execute_input":"2022-11-10T19:27:55.350354Z","iopub.status.idle":"2022-11-10T19:30:30.153522Z","shell.execute_reply.started":"2022-11-10T19:27:55.350313Z","shell.execute_reply":"2022-11-10T19:30:30.152226Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"category_dfs = sorted(category_dfs, key=lambda x: -x[\"df\"].shape[0])","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:30:30.154767Z","iopub.execute_input":"2022-11-10T19:30:30.155117Z","iopub.status.idle":"2022-11-10T19:30:30.160887Z","shell.execute_reply.started":"2022-11-10T19:30:30.155085Z","shell.execute_reply":"2022-11-10T19:30:30.159764Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(len(category_dfs))\nprint(sum(cat[\"races\"] for cat in category_dfs))","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2022-11-10T19:30:30.162640Z","iopub.execute_input":"2022-11-10T19:30:30.163521Z","iopub.status.idle":"2022-11-10T19:30:30.172757Z","shell.execute_reply.started":"2022-11-10T19:30:30.163475Z","shell.execute_reply":"2022-11-10T19:30:30.171699Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"title_texts = []\nfor i, category_df in enumerate(category_dfs):\n cat = category_df['category']\n races = category_df[\"races\"]\n \n title_text = f\"

Category {i+1}

\"\n \n title_text += f\"

Track: {id_maps['track_id'][cat['track_id']]}
\"\n title_text += f\"Track Condition: {id_maps['track_condition'][cat['track_condition']]}
\"\n title_text += f\"Course Type: {id_maps['course_type'][cat['course_type']]}
\"\n \n title_text += f\"Race Type: {id_maps['race_type'][cat['race_type']]}
\"\n title_text += f\"Distance: {cat['distance_id'] / 100} furlongs
\"\n title_text += f\"Runup Distance {cat['run_up_distance_bins']} feet

\"\n \n title_text += f\"

Number of Races: {races}

\"\n \n title_texts.append(title_text)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:30:30.174086Z","iopub.execute_input":"2022-11-10T19:30:30.174444Z","iopub.status.idle":"2022-11-10T19:30:30.184549Z","shell.execute_reply.started":"2022-11-10T19:30:30.174412Z","shell.execute_reply":"2022-11-10T19:30:30.183511Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Introduction","metadata":{}},{"cell_type":"markdown","source":"In this study, we will be finding the **best performing racing strategies**, using the data gathered for the Big Data Derby 2022.
\nOur objective is to help **owners**, **trainers** and **jockeys** win more races more consistently.
\nTo do so, we will exctract a few Key Performance Indicators (KPIs) for a subset of races, but only analyzing them for the **winners of each race**.
\nWe will be doing so across **12 different categories of races**, each having distinct values in the 6 following race characteristics: \n* race **track** (Aqueduct, Belmont or Saratoga)\n* race **distance** (measured in furlongs)\n* **course type**\n* **track condition**\n* **race type**\n* race **run up distance** (roundend to the nearest 5 feet) \n\nThe total number of races taken into account in this study is 232.
","metadata":{}},{"cell_type":"markdown","source":"Our model to build the Optimal Jockey and Horse Combo will be based on the 3 following actions on the dataset:\n1. Taking only the **winners of each race**.\n2. Generating **4 Key Performance Indicators (KPIs)**.\n3. **Aggregating the winners' KPIs** for each of the 12 categories \n\nBy taking these actions we aim to find a **general data driven model** to achieve a **winning strategy** in different racing conditions.","metadata":{}},{"cell_type":"markdown","source":"The KPIs we will be finding are the following: \n* [Optimal Path](#2)\n* [Optimal Velocity](#3)\n* [Optimal Acceleration](#4)\n* [Optimal Jockey Weight](#5)","metadata":{}},{"cell_type":"markdown","source":"At the end of this study, there will be a [KPI Dashboard](#6) that will let you explore these KPIs for each of the 12 categories.","metadata":{}},{"cell_type":"markdown","source":"## Key Results","metadata":{}},{"cell_type":"code","source":"peak_list = []\n\nfor category in category_dfs:\n category_df = category[\"df\"]\n agg_df = category_df.groupby('seconds')[['latitude', 'longitude', 'velocity', 'acceleration']].mean().reset_index(level=0)\n peak_vel = agg_df['velocity'].max()\n \n peak_list.append(\n {\"Peak Velocity (km/h)\": peak_vel, \"Distance (furlongs)\": category[\"category\"][\"distance_id\"] / 100}\n )\n\npeak_df = pd.DataFrame(peak_list)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:31:56.385537Z","iopub.execute_input":"2022-11-10T19:31:56.386643Z","iopub.status.idle":"2022-11-10T19:31:56.425661Z","shell.execute_reply.started":"2022-11-10T19:31:56.386594Z","shell.execute_reply":"2022-11-10T19:31:56.424624Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Before we go through the details, we will give the general strategy that we have found to be optimal in most races.","metadata":{}},{"cell_type":"markdown","source":"The optimal strategy is to reach a peak velocity in the range of **73-80 km/h** within the **first 15 seconds** of the race.
\nThen it is important to keep your velocity in the **60-70 km/h range during the curve**.
\nAfter the curve, velocity inevitably tapers off due to fatigue, as measured by the **high acceleration of around 0.1 m / s^2 during the curve**.
\nHowever, keeping a velocity **above 60km/h in the final stretch** is key.
\nThe optimal **jockey weight** to allow for all of the above is **around 121 lbs**.","metadata":{}},{"cell_type":"markdown","source":"Regarding all velocity ranges above, the **longer the distance** of the race, the **lower the velocity** will be, given the set amount of horse stamina.
\nWe can view this relationship for peak velocity below.","metadata":{}},{"cell_type":"code","source":"fig = px.box(peak_df, x='Distance (furlongs)', y='Peak Velocity (km/h)')\nfig.update_layout(title='Distance and Peak Velocity', template=\"plotly_white\")\nfig.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:31:58.678627Z","iopub.execute_input":"2022-11-10T19:31:58.679460Z","iopub.status.idle":"2022-11-10T19:31:59.848780Z","shell.execute_reply.started":"2022-11-10T19:31:58.679411Z","shell.execute_reply":"2022-11-10T19:31:59.847565Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n# 2. Optimal Path","metadata":{}},{"cell_type":"markdown","source":"In the next 4 sections we will be exploring our 4 KPIs only for the category with the following race characteristics:","metadata":{}},{"cell_type":"code","source":"display(HTML(title_texts[4][19:]))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:32:07.377075Z","iopub.execute_input":"2022-11-10T19:32:07.377963Z","iopub.status.idle":"2022-11-10T19:32:07.386050Z","shell.execute_reply.started":"2022-11-10T19:32:07.377902Z","shell.execute_reply":"2022-11-10T19:32:07.384964Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"In the KPI Dashboard section, we will examine the 4 KPIs across all of the 12 categories.","metadata":{}},{"cell_type":"markdown","source":"Let us take a look at the optimal race path.
\nThe following is the average path that was taken by the winners of the 23 races in this category.
\nWe have overlayed this path over satellite imagery of the Aqueduct racing track, to give the best possible view of the optimal race to stakeholders.","metadata":{}},{"cell_type":"code","source":"def plot_path(df, vel=True, acc=True):\n scale = px.colors.sequential.Plasma\n if vel is True and acc is True:\n fig = px.scatter_mapbox(\n df, lat='latitude', lon='longitude', color='velocity', \n color_continuous_scale=scale,\n hover_data=['latitude', 'longitude', 'velocity', 'acceleration', 'seconds'],\n zoom=14.8\n )\n elif vel is True:\n fig = px.scatter_mapbox(\n df, lat='latitude', lon='longitude', color='velocity',\n color_continuous_scale=scale,\n hover_data=['latitude', 'longitude', 'velocity', 'seconds'],\n zoom=14.8\n )\n elif acc is True:\n scale = px.colors.sequential.Viridis\n fig = px.scatter_mapbox(\n df, lat='latitude', lon='longitude', color='acceleration', \n color_continuous_scale=scale,\n hover_data=['latitude', 'longitude', 'velocity', 'acceleration', 'seconds'],\n zoom=14.8\n )\n else:\n fig = px.scatter_mapbox(\n df, lat='latitude', lon='longitude',\n hover_data=['latitude', 'longitude', 'seconds'],\n zoom=14.8, size_max=0.5\n )\n\n fig.update_layout(\n mapbox_style=\"white-bg\",\n mapbox_layers=[\n {\n \"below\": 'traces',\n \"sourcetype\": \"raster\",\n \"sourceattribution\": \"United States Geological Survey\",\n \"source\": [\n \"https://basemap.nationalmap.gov/arcgis/rest/services/USGSImageryOnly/MapServer/tile/{z}/{y}/{x}\"\n ]\n }\n ],\n template='plotly_white',\n height=800,\n title='Race Path'\n )\n \n return fig","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:32:53.359172Z","iopub.execute_input":"2022-11-10T19:32:53.359675Z","iopub.status.idle":"2022-11-10T19:32:53.371881Z","shell.execute_reply.started":"2022-11-10T19:32:53.359634Z","shell.execute_reply":"2022-11-10T19:32:53.370390Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def plot_velocity(df):\n fig = go.Figure()\n\n fig.add_traces(\n go.Scatter(\n x=df['seconds'],\n y=df['velocity'],\n name='Velocity',\n mode='markers'\n\n )\n )\n rolling_average = df.set_index('seconds')['velocity'].rolling(20).mean()\n\n fig.add_traces(\n go.Scatter(\n x=rolling_average.index,\n y=rolling_average,\n name='Rolling Avg (5s)',\n line=dict(color='red')\n )\n )\n\n fig.update_layout(\n template='plotly_white',\n xaxis_title=\"seconds\",\n yaxis_title=\"km/h\",\n height=500,\n title=\"Velocity over Time\"\n )\n\n return fig","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:32:54.163245Z","iopub.execute_input":"2022-11-10T19:32:54.163712Z","iopub.status.idle":"2022-11-10T19:32:54.172244Z","shell.execute_reply.started":"2022-11-10T19:32:54.163666Z","shell.execute_reply":"2022-11-10T19:32:54.170982Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def plot_acceleration(df):\n fig = go.Figure()\n\n fig.add_traces(\n go.Scatter(\n x=df['seconds'],\n y=df['acceleration'],\n name='Acceleration',\n mode='markers',\n line=dict(color='green')\n\n )\n )\n\n rolling_average = df.set_index('seconds')['acceleration'].rolling(20).mean()\n\n fig.add_traces(\n go.Scatter(\n x=rolling_average.index,\n y=rolling_average,\n name='Rolling Avg (5s)',\n line=dict(color='red')\n )\n )\n\n fig.update_layout(\n template='plotly_white',\n xaxis_title=\"seconds\",\n yaxis_title=\"m/s^2\",\n height=500,\n title=\"Acceleration over Time\"\n )\n\n return fig","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:32:54.581862Z","iopub.execute_input":"2022-11-10T19:32:54.582368Z","iopub.status.idle":"2022-11-10T19:32:54.592145Z","shell.execute_reply.started":"2022-11-10T19:32:54.582317Z","shell.execute_reply":"2022-11-10T19:32:54.590690Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cat = 4\ncategory = category_dfs[cat][\"category\"]\ncategory_df = category_dfs[cat][\"df\"]\n\nprint(category)\ncategory_df","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2022-11-10T19:32:55.122412Z","iopub.execute_input":"2022-11-10T19:32:55.122868Z","iopub.status.idle":"2022-11-10T19:32:55.167102Z","shell.execute_reply.started":"2022-11-10T19:32:55.122831Z","shell.execute_reply":"2022-11-10T19:32:55.165886Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# mean\nagg_df = category_df.groupby('seconds')[['latitude', 'longitude', 'velocity', 'acceleration']].mean().reset_index(level=0)\nagg_df","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2022-11-10T19:32:55.571306Z","iopub.execute_input":"2022-11-10T19:32:55.572685Z","iopub.status.idle":"2022-11-10T19:32:55.592996Z","shell.execute_reply.started":"2022-11-10T19:32:55.572637Z","shell.execute_reply":"2022-11-10T19:32:55.591846Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# mean\nplot_path(agg_df, vel=False, acc=False)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:32:56.660063Z","iopub.execute_input":"2022-11-10T19:32:56.660579Z","iopub.status.idle":"2022-11-10T19:32:56.789617Z","shell.execute_reply.started":"2022-11-10T19:32:56.660539Z","shell.execute_reply":"2022-11-10T19:32:56.788570Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n# 3. Optimal Velocity","metadata":{}},{"cell_type":"markdown","source":"Let us now examine optimal Velocity evolution during the race, as per the average of the 23 winners.
\nWe have added a 5 second rolling average to the graph to smooth out statistical noise in the data.","metadata":{}},{"cell_type":"code","source":"# mean\nplot_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:33:04.158035Z","iopub.execute_input":"2022-11-10T19:33:04.158463Z","iopub.status.idle":"2022-11-10T19:33:04.207852Z","shell.execute_reply.started":"2022-11-10T19:33:04.158430Z","shell.execute_reply":"2022-11-10T19:33:04.206784Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def print_peak_velocity(df):\n display(HTML(f\"

Peak velocity: {df['velocity'].max():.2f} km/h

\"))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:33:04.519542Z","iopub.execute_input":"2022-11-10T19:33:04.520012Z","iopub.status.idle":"2022-11-10T19:33:04.525213Z","shell.execute_reply.started":"2022-11-10T19:33:04.519972Z","shell.execute_reply":"2022-11-10T19:33:04.524184Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_peak_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:33:04.983570Z","iopub.execute_input":"2022-11-10T19:33:04.984034Z","iopub.status.idle":"2022-11-10T19:33:04.992516Z","shell.execute_reply.started":"2022-11-10T19:33:04.983997Z","shell.execute_reply":"2022-11-10T19:33:04.991163Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We will now combine path and velocity data to create a detailed view of velocity evolution during the race.","metadata":{}},{"cell_type":"code","source":"plot_path(agg_df, vel=True, acc=False)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:33:06.569259Z","iopub.execute_input":"2022-11-10T19:33:06.569692Z","iopub.status.idle":"2022-11-10T19:33:06.671165Z","shell.execute_reply.started":"2022-11-10T19:33:06.569660Z","shell.execute_reply":"2022-11-10T19:33:06.669993Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n# 4. Optimal Acceleration","metadata":{}},{"cell_type":"markdown","source":"Our last physical metric that evolves over time will be acceleration.
\nAgain, we have added a 5 second rolling average to smooth out statistical noise.","metadata":{}},{"cell_type":"code","source":"# mean\nplot_acceleration(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:33:08.961597Z","iopub.execute_input":"2022-11-10T19:33:08.962486Z","iopub.status.idle":"2022-11-10T19:33:09.002179Z","shell.execute_reply.started":"2022-11-10T19:33:08.962442Z","shell.execute_reply":"2022-11-10T19:33:09.001085Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Again let us combine path and acceleration data, to see the optimal acceleration evolution over time, as per the 23 winners.","metadata":{}},{"cell_type":"code","source":"plot_path(agg_df, vel=False, acc=True)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:33:10.351385Z","iopub.execute_input":"2022-11-10T19:33:10.352288Z","iopub.status.idle":"2022-11-10T19:33:10.438820Z","shell.execute_reply.started":"2022-11-10T19:33:10.352247Z","shell.execute_reply":"2022-11-10T19:33:10.437713Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n# 5. Optimal Jockey Weight","metadata":{}},{"cell_type":"markdown","source":"We will now examine the winning jockey weight distribution within this category, and also derive the winning jockey average weight.","metadata":{}},{"cell_type":"code","source":"def plot_weight(df):\n fig = px.histogram(df, x='weight_carried')\n fig.update_layout(\n title=\"Jockey Weight Distribution\",\n xaxis_title=\"lbs\",\n template=\"plotly_white\"\n )\n return fig","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:33:12.388693Z","iopub.execute_input":"2022-11-10T19:33:12.389585Z","iopub.status.idle":"2022-11-10T19:33:12.396382Z","shell.execute_reply.started":"2022-11-10T19:33:12.389525Z","shell.execute_reply":"2022-11-10T19:33:12.395163Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def print_weight(df):\n display(HTML(f\"

Average Jockey Weight: {df['weight_carried'].mean():.2f} lbs

\"))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:33:12.938880Z","iopub.execute_input":"2022-11-10T19:33:12.939838Z","iopub.status.idle":"2022-11-10T19:33:12.944793Z","shell.execute_reply.started":"2022-11-10T19:33:12.939797Z","shell.execute_reply":"2022-11-10T19:33:12.943666Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"weight_df = category_df.groupby('racer_id')['weight_carried'].first().to_frame()\nweight_df","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2022-11-10T19:33:14.566804Z","iopub.execute_input":"2022-11-10T19:33:14.567433Z","iopub.status.idle":"2022-11-10T19:33:14.581540Z","shell.execute_reply.started":"2022-11-10T19:33:14.567391Z","shell.execute_reply":"2022-11-10T19:33:14.580024Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_weight(weight_df).show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:33:15.617359Z","iopub.execute_input":"2022-11-10T19:33:15.617834Z","iopub.status.idle":"2022-11-10T19:33:15.715837Z","shell.execute_reply.started":"2022-11-10T19:33:15.617799Z","shell.execute_reply":"2022-11-10T19:33:15.714564Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:33:16.191369Z","iopub.execute_input":"2022-11-10T19:33:16.191812Z","iopub.status.idle":"2022-11-10T19:33:16.199996Z","shell.execute_reply.started":"2022-11-10T19:33:16.191776Z","shell.execute_reply":"2022-11-10T19:33:16.198394Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n# 6. KPI Dashboard","metadata":{}},{"cell_type":"markdown","source":"We will now display a dashboard for each of the 12 categories, containing the KPIs defined above.","metadata":{}},{"cell_type":"code","source":"cat = 0","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:34:31.815972Z","iopub.execute_input":"2022-11-10T19:34:31.817333Z","iopub.status.idle":"2022-11-10T19:34:31.822323Z","shell.execute_reply.started":"2022-11-10T19:34:31.817283Z","shell.execute_reply":"2022-11-10T19:34:31.821346Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display(HTML(title_texts[cat]))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:34:33.278320Z","iopub.execute_input":"2022-11-10T19:34:33.278773Z","iopub.status.idle":"2022-11-10T19:34:33.286913Z","shell.execute_reply.started":"2022-11-10T19:34:33.278737Z","shell.execute_reply":"2022-11-10T19:34:33.285373Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"category_df = category_dfs[cat][\"df\"]\n\nagg_df = category_df.groupby('seconds')[['latitude', 'longitude', 'velocity', 'acceleration']].mean().reset_index(level=0)\nweight_df = category_df.groupby('racer_id')['weight_carried'].first().to_frame()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:34:33.683893Z","iopub.execute_input":"2022-11-10T19:34:33.684775Z","iopub.status.idle":"2022-11-10T19:34:33.698096Z","shell.execute_reply.started":"2022-11-10T19:34:33.684725Z","shell.execute_reply":"2022-11-10T19:34:33.696522Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_path(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:34:34.729405Z","iopub.execute_input":"2022-11-10T19:34:34.729864Z","iopub.status.idle":"2022-11-10T19:34:34.824105Z","shell.execute_reply.started":"2022-11-10T19:34:34.729828Z","shell.execute_reply":"2022-11-10T19:34:34.822982Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:34:38.359102Z","iopub.execute_input":"2022-11-10T19:34:38.359548Z","iopub.status.idle":"2022-11-10T19:34:38.400128Z","shell.execute_reply.started":"2022-11-10T19:34:38.359510Z","shell.execute_reply":"2022-11-10T19:34:38.398924Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_peak_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:34:38.607546Z","iopub.execute_input":"2022-11-10T19:34:38.608025Z","iopub.status.idle":"2022-11-10T19:34:38.615584Z","shell.execute_reply.started":"2022-11-10T19:34:38.607986Z","shell.execute_reply":"2022-11-10T19:34:38.614199Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_acceleration(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:34:39.256131Z","iopub.execute_input":"2022-11-10T19:34:39.256566Z","iopub.status.idle":"2022-11-10T19:34:39.294850Z","shell.execute_reply.started":"2022-11-10T19:34:39.256530Z","shell.execute_reply":"2022-11-10T19:34:39.293701Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:34:42.901670Z","iopub.execute_input":"2022-11-10T19:34:42.902103Z","iopub.status.idle":"2022-11-10T19:34:42.979780Z","shell.execute_reply.started":"2022-11-10T19:34:42.902070Z","shell.execute_reply":"2022-11-10T19:34:42.978996Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:34:43.971704Z","iopub.execute_input":"2022-11-10T19:34:43.972667Z","iopub.status.idle":"2022-11-10T19:34:43.979410Z","shell.execute_reply.started":"2022-11-10T19:34:43.972629Z","shell.execute_reply":"2022-11-10T19:34:43.978624Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cat = 1","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:24.220063Z","iopub.execute_input":"2022-11-10T19:35:24.220548Z","iopub.status.idle":"2022-11-10T19:35:24.225802Z","shell.execute_reply.started":"2022-11-10T19:35:24.220509Z","shell.execute_reply":"2022-11-10T19:35:24.224726Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display(HTML(title_texts[cat]))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:24.227847Z","iopub.execute_input":"2022-11-10T19:35:24.228231Z","iopub.status.idle":"2022-11-10T19:35:24.241747Z","shell.execute_reply.started":"2022-11-10T19:35:24.228198Z","shell.execute_reply":"2022-11-10T19:35:24.240520Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"category_df = category_dfs[cat][\"df\"]\n\nagg_df = category_df.groupby('seconds')[['latitude', 'longitude', 'velocity', 'acceleration']].mean().reset_index(level=0)\nweight_df = category_df.groupby('racer_id')['weight_carried'].first().to_frame()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:24.472360Z","iopub.execute_input":"2022-11-10T19:35:24.472862Z","iopub.status.idle":"2022-11-10T19:35:24.484060Z","shell.execute_reply.started":"2022-11-10T19:35:24.472824Z","shell.execute_reply":"2022-11-10T19:35:24.483008Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_path(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:24.485897Z","iopub.execute_input":"2022-11-10T19:35:24.486554Z","iopub.status.idle":"2022-11-10T19:35:24.572635Z","shell.execute_reply.started":"2022-11-10T19:35:24.486521Z","shell.execute_reply":"2022-11-10T19:35:24.571567Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:24.574680Z","iopub.execute_input":"2022-11-10T19:35:24.575511Z","iopub.status.idle":"2022-11-10T19:35:24.614125Z","shell.execute_reply.started":"2022-11-10T19:35:24.575466Z","shell.execute_reply":"2022-11-10T19:35:24.612969Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_peak_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:24.616025Z","iopub.execute_input":"2022-11-10T19:35:24.616728Z","iopub.status.idle":"2022-11-10T19:35:24.624754Z","shell.execute_reply.started":"2022-11-10T19:35:24.616694Z","shell.execute_reply":"2022-11-10T19:35:24.623715Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_acceleration(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:24.628340Z","iopub.execute_input":"2022-11-10T19:35:24.629170Z","iopub.status.idle":"2022-11-10T19:35:24.669494Z","shell.execute_reply.started":"2022-11-10T19:35:24.629132Z","shell.execute_reply":"2022-11-10T19:35:24.668288Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:24.670850Z","iopub.execute_input":"2022-11-10T19:35:24.671190Z","iopub.status.idle":"2022-11-10T19:35:24.750575Z","shell.execute_reply.started":"2022-11-10T19:35:24.671162Z","shell.execute_reply":"2022-11-10T19:35:24.749511Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:24.752570Z","iopub.execute_input":"2022-11-10T19:35:24.753061Z","iopub.status.idle":"2022-11-10T19:35:24.760792Z","shell.execute_reply.started":"2022-11-10T19:35:24.753014Z","shell.execute_reply":"2022-11-10T19:35:24.759750Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cat = 2","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:24.763065Z","iopub.execute_input":"2022-11-10T19:35:24.763590Z","iopub.status.idle":"2022-11-10T19:35:24.769772Z","shell.execute_reply.started":"2022-11-10T19:35:24.763548Z","shell.execute_reply":"2022-11-10T19:35:24.768873Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display(HTML(title_texts[cat]))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:24.773869Z","iopub.execute_input":"2022-11-10T19:35:24.774618Z","iopub.status.idle":"2022-11-10T19:35:24.782632Z","shell.execute_reply.started":"2022-11-10T19:35:24.774570Z","shell.execute_reply":"2022-11-10T19:35:24.781633Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"category_df = category_dfs[cat][\"df\"]\n\nagg_df = category_df.groupby('seconds')[['latitude', 'longitude', 'velocity', 'acceleration']].mean().reset_index(level=0)\nweight_df = category_df.groupby('racer_id')['weight_carried'].first().to_frame()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:24.784637Z","iopub.execute_input":"2022-11-10T19:35:24.785103Z","iopub.status.idle":"2022-11-10T19:35:24.797459Z","shell.execute_reply.started":"2022-11-10T19:35:24.785060Z","shell.execute_reply":"2022-11-10T19:35:24.796444Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_path(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:24.802916Z","iopub.execute_input":"2022-11-10T19:35:24.803266Z","iopub.status.idle":"2022-11-10T19:35:24.894881Z","shell.execute_reply.started":"2022-11-10T19:35:24.803237Z","shell.execute_reply":"2022-11-10T19:35:24.893614Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:24.897265Z","iopub.execute_input":"2022-11-10T19:35:24.897752Z","iopub.status.idle":"2022-11-10T19:35:24.937052Z","shell.execute_reply.started":"2022-11-10T19:35:24.897708Z","shell.execute_reply":"2022-11-10T19:35:24.935993Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_peak_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:24.938895Z","iopub.execute_input":"2022-11-10T19:35:24.939527Z","iopub.status.idle":"2022-11-10T19:35:24.947254Z","shell.execute_reply.started":"2022-11-10T19:35:24.939483Z","shell.execute_reply":"2022-11-10T19:35:24.946140Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_acceleration(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:24.949011Z","iopub.execute_input":"2022-11-10T19:35:24.949323Z","iopub.status.idle":"2022-11-10T19:35:24.997880Z","shell.execute_reply.started":"2022-11-10T19:35:24.949296Z","shell.execute_reply":"2022-11-10T19:35:24.996643Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:24.999491Z","iopub.execute_input":"2022-11-10T19:35:24.999818Z","iopub.status.idle":"2022-11-10T19:35:25.079016Z","shell.execute_reply.started":"2022-11-10T19:35:24.999790Z","shell.execute_reply":"2022-11-10T19:35:25.078173Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.080261Z","iopub.execute_input":"2022-11-10T19:35:25.080752Z","iopub.status.idle":"2022-11-10T19:35:25.087835Z","shell.execute_reply.started":"2022-11-10T19:35:25.080721Z","shell.execute_reply":"2022-11-10T19:35:25.086159Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cat = 3","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.090138Z","iopub.execute_input":"2022-11-10T19:35:25.090913Z","iopub.status.idle":"2022-11-10T19:35:25.097488Z","shell.execute_reply.started":"2022-11-10T19:35:25.090864Z","shell.execute_reply":"2022-11-10T19:35:25.096417Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display(HTML(title_texts[cat]))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.098926Z","iopub.execute_input":"2022-11-10T19:35:25.099311Z","iopub.status.idle":"2022-11-10T19:35:25.110826Z","shell.execute_reply.started":"2022-11-10T19:35:25.099281Z","shell.execute_reply":"2022-11-10T19:35:25.109660Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"category_df = category_dfs[cat][\"df\"]\n\nagg_df = category_df.groupby('seconds')[['latitude', 'longitude', 'velocity', 'acceleration']].mean().reset_index(level=0)\nweight_df = category_df.groupby('racer_id')['weight_carried'].first().to_frame()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.112503Z","iopub.execute_input":"2022-11-10T19:35:25.113234Z","iopub.status.idle":"2022-11-10T19:35:25.125708Z","shell.execute_reply.started":"2022-11-10T19:35:25.113199Z","shell.execute_reply":"2022-11-10T19:35:25.124747Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_path(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.127157Z","iopub.execute_input":"2022-11-10T19:35:25.127624Z","iopub.status.idle":"2022-11-10T19:35:25.221883Z","shell.execute_reply.started":"2022-11-10T19:35:25.127596Z","shell.execute_reply":"2022-11-10T19:35:25.220994Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.223669Z","iopub.execute_input":"2022-11-10T19:35:25.224268Z","iopub.status.idle":"2022-11-10T19:35:25.263223Z","shell.execute_reply.started":"2022-11-10T19:35:25.224235Z","shell.execute_reply":"2022-11-10T19:35:25.262119Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_peak_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.264933Z","iopub.execute_input":"2022-11-10T19:35:25.265471Z","iopub.status.idle":"2022-11-10T19:35:25.274110Z","shell.execute_reply.started":"2022-11-10T19:35:25.265426Z","shell.execute_reply":"2022-11-10T19:35:25.272928Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_acceleration(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.276417Z","iopub.execute_input":"2022-11-10T19:35:25.277212Z","iopub.status.idle":"2022-11-10T19:35:25.315896Z","shell.execute_reply.started":"2022-11-10T19:35:25.277156Z","shell.execute_reply":"2022-11-10T19:35:25.314834Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.317720Z","iopub.execute_input":"2022-11-10T19:35:25.318316Z","iopub.status.idle":"2022-11-10T19:35:25.396850Z","shell.execute_reply.started":"2022-11-10T19:35:25.318284Z","shell.execute_reply":"2022-11-10T19:35:25.395797Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.398318Z","iopub.execute_input":"2022-11-10T19:35:25.398652Z","iopub.status.idle":"2022-11-10T19:35:25.405588Z","shell.execute_reply.started":"2022-11-10T19:35:25.398622Z","shell.execute_reply":"2022-11-10T19:35:25.404576Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cat = 4","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.407356Z","iopub.execute_input":"2022-11-10T19:35:25.407688Z","iopub.status.idle":"2022-11-10T19:35:25.416357Z","shell.execute_reply.started":"2022-11-10T19:35:25.407658Z","shell.execute_reply":"2022-11-10T19:35:25.415387Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display(HTML(title_texts[cat]))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.425338Z","iopub.execute_input":"2022-11-10T19:35:25.425814Z","iopub.status.idle":"2022-11-10T19:35:25.433587Z","shell.execute_reply.started":"2022-11-10T19:35:25.425755Z","shell.execute_reply":"2022-11-10T19:35:25.432277Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"category_df = category_dfs[cat][\"df\"]\n\nagg_df = category_df.groupby('seconds')[['latitude', 'longitude', 'velocity', 'acceleration']].mean().reset_index(level=0)\nweight_df = category_df.groupby('racer_id')['weight_carried'].first().to_frame()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.434897Z","iopub.execute_input":"2022-11-10T19:35:25.435317Z","iopub.status.idle":"2022-11-10T19:35:25.448099Z","shell.execute_reply.started":"2022-11-10T19:35:25.435282Z","shell.execute_reply":"2022-11-10T19:35:25.446993Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_path(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.449914Z","iopub.execute_input":"2022-11-10T19:35:25.450484Z","iopub.status.idle":"2022-11-10T19:35:25.543144Z","shell.execute_reply.started":"2022-11-10T19:35:25.450439Z","shell.execute_reply":"2022-11-10T19:35:25.542127Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.545765Z","iopub.execute_input":"2022-11-10T19:35:25.546118Z","iopub.status.idle":"2022-11-10T19:35:25.584610Z","shell.execute_reply.started":"2022-11-10T19:35:25.546085Z","shell.execute_reply":"2022-11-10T19:35:25.583562Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_peak_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.586137Z","iopub.execute_input":"2022-11-10T19:35:25.586441Z","iopub.status.idle":"2022-11-10T19:35:25.593410Z","shell.execute_reply.started":"2022-11-10T19:35:25.586413Z","shell.execute_reply":"2022-11-10T19:35:25.592441Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_acceleration(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.595532Z","iopub.execute_input":"2022-11-10T19:35:25.596013Z","iopub.status.idle":"2022-11-10T19:35:25.636832Z","shell.execute_reply.started":"2022-11-10T19:35:25.595901Z","shell.execute_reply":"2022-11-10T19:35:25.635722Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.639641Z","iopub.execute_input":"2022-11-10T19:35:25.640085Z","iopub.status.idle":"2022-11-10T19:35:25.721817Z","shell.execute_reply.started":"2022-11-10T19:35:25.640042Z","shell.execute_reply":"2022-11-10T19:35:25.720703Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.723607Z","iopub.execute_input":"2022-11-10T19:35:25.724076Z","iopub.status.idle":"2022-11-10T19:35:25.731635Z","shell.execute_reply.started":"2022-11-10T19:35:25.724034Z","shell.execute_reply":"2022-11-10T19:35:25.730534Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cat = 5","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.733413Z","iopub.execute_input":"2022-11-10T19:35:25.733769Z","iopub.status.idle":"2022-11-10T19:35:25.740968Z","shell.execute_reply.started":"2022-11-10T19:35:25.733738Z","shell.execute_reply":"2022-11-10T19:35:25.739823Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display(HTML(title_texts[cat]))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.742456Z","iopub.execute_input":"2022-11-10T19:35:25.742780Z","iopub.status.idle":"2022-11-10T19:35:25.753660Z","shell.execute_reply.started":"2022-11-10T19:35:25.742747Z","shell.execute_reply":"2022-11-10T19:35:25.752533Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"category_df = category_dfs[cat][\"df\"]\n\nagg_df = category_df.groupby('seconds')[['latitude', 'longitude', 'velocity', 'acceleration']].mean().reset_index(level=0)\nweight_df = category_df.groupby('racer_id')['weight_carried'].first().to_frame()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.755393Z","iopub.execute_input":"2022-11-10T19:35:25.755719Z","iopub.status.idle":"2022-11-10T19:35:25.769549Z","shell.execute_reply.started":"2022-11-10T19:35:25.755692Z","shell.execute_reply":"2022-11-10T19:35:25.768499Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_path(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.771442Z","iopub.execute_input":"2022-11-10T19:35:25.772131Z","iopub.status.idle":"2022-11-10T19:35:25.856566Z","shell.execute_reply.started":"2022-11-10T19:35:25.772096Z","shell.execute_reply":"2022-11-10T19:35:25.855490Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.858190Z","iopub.execute_input":"2022-11-10T19:35:25.858544Z","iopub.status.idle":"2022-11-10T19:35:25.900489Z","shell.execute_reply.started":"2022-11-10T19:35:25.858512Z","shell.execute_reply":"2022-11-10T19:35:25.899577Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_peak_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.902541Z","iopub.execute_input":"2022-11-10T19:35:25.903382Z","iopub.status.idle":"2022-11-10T19:35:25.911432Z","shell.execute_reply.started":"2022-11-10T19:35:25.903338Z","shell.execute_reply":"2022-11-10T19:35:25.910409Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_acceleration(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.913001Z","iopub.execute_input":"2022-11-10T19:35:25.913452Z","iopub.status.idle":"2022-11-10T19:35:25.958258Z","shell.execute_reply.started":"2022-11-10T19:35:25.913409Z","shell.execute_reply":"2022-11-10T19:35:25.957219Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:25.959973Z","iopub.execute_input":"2022-11-10T19:35:25.960296Z","iopub.status.idle":"2022-11-10T19:35:26.208050Z","shell.execute_reply.started":"2022-11-10T19:35:25.960268Z","shell.execute_reply":"2022-11-10T19:35:26.206951Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:26.210147Z","iopub.execute_input":"2022-11-10T19:35:26.210671Z","iopub.status.idle":"2022-11-10T19:35:26.218244Z","shell.execute_reply.started":"2022-11-10T19:35:26.210621Z","shell.execute_reply":"2022-11-10T19:35:26.217014Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cat = 6","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:26.220498Z","iopub.execute_input":"2022-11-10T19:35:26.221008Z","iopub.status.idle":"2022-11-10T19:35:26.227988Z","shell.execute_reply.started":"2022-11-10T19:35:26.220960Z","shell.execute_reply":"2022-11-10T19:35:26.227004Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display(HTML(title_texts[cat]))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:26.229264Z","iopub.execute_input":"2022-11-10T19:35:26.229595Z","iopub.status.idle":"2022-11-10T19:35:26.241595Z","shell.execute_reply.started":"2022-11-10T19:35:26.229566Z","shell.execute_reply":"2022-11-10T19:35:26.240519Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"category_df = category_dfs[cat][\"df\"]\n\nagg_df = category_df.groupby('seconds')[['latitude', 'longitude', 'velocity', 'acceleration']].mean().reset_index(level=0)\nweight_df = category_df.groupby('racer_id')['weight_carried'].first().to_frame()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:26.243150Z","iopub.execute_input":"2022-11-10T19:35:26.243675Z","iopub.status.idle":"2022-11-10T19:35:26.255505Z","shell.execute_reply.started":"2022-11-10T19:35:26.243643Z","shell.execute_reply":"2022-11-10T19:35:26.254570Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_path(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:26.257196Z","iopub.execute_input":"2022-11-10T19:35:26.257625Z","iopub.status.idle":"2022-11-10T19:35:26.346393Z","shell.execute_reply.started":"2022-11-10T19:35:26.257593Z","shell.execute_reply":"2022-11-10T19:35:26.345293Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:26.348082Z","iopub.execute_input":"2022-11-10T19:35:26.348438Z","iopub.status.idle":"2022-11-10T19:35:26.389073Z","shell.execute_reply.started":"2022-11-10T19:35:26.348406Z","shell.execute_reply":"2022-11-10T19:35:26.388111Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_peak_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:26.390393Z","iopub.execute_input":"2022-11-10T19:35:26.390746Z","iopub.status.idle":"2022-11-10T19:35:26.397766Z","shell.execute_reply.started":"2022-11-10T19:35:26.390714Z","shell.execute_reply":"2022-11-10T19:35:26.396562Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_acceleration(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:26.398923Z","iopub.execute_input":"2022-11-10T19:35:26.399279Z","iopub.status.idle":"2022-11-10T19:35:26.443278Z","shell.execute_reply.started":"2022-11-10T19:35:26.399233Z","shell.execute_reply":"2022-11-10T19:35:26.442154Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:26.445295Z","iopub.execute_input":"2022-11-10T19:35:26.445712Z","iopub.status.idle":"2022-11-10T19:35:26.524743Z","shell.execute_reply.started":"2022-11-10T19:35:26.445670Z","shell.execute_reply":"2022-11-10T19:35:26.523818Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:26.526485Z","iopub.execute_input":"2022-11-10T19:35:26.526817Z","iopub.status.idle":"2022-11-10T19:35:26.534366Z","shell.execute_reply.started":"2022-11-10T19:35:26.526786Z","shell.execute_reply":"2022-11-10T19:35:26.533272Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cat = 7","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:26.536282Z","iopub.execute_input":"2022-11-10T19:35:26.536651Z","iopub.status.idle":"2022-11-10T19:35:26.543068Z","shell.execute_reply.started":"2022-11-10T19:35:26.536621Z","shell.execute_reply":"2022-11-10T19:35:26.542065Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display(HTML(title_texts[cat]))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:26.544546Z","iopub.execute_input":"2022-11-10T19:35:26.545118Z","iopub.status.idle":"2022-11-10T19:35:26.554138Z","shell.execute_reply.started":"2022-11-10T19:35:26.545078Z","shell.execute_reply":"2022-11-10T19:35:26.553077Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"category_df = category_dfs[cat][\"df\"]\n\nagg_df = category_df.groupby('seconds')[['latitude', 'longitude', 'velocity', 'acceleration']].mean().reset_index(level=0)\nweight_df = category_df.groupby('racer_id')['weight_carried'].first().to_frame()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:26.555432Z","iopub.execute_input":"2022-11-10T19:35:26.555716Z","iopub.status.idle":"2022-11-10T19:35:26.569042Z","shell.execute_reply.started":"2022-11-10T19:35:26.555690Z","shell.execute_reply":"2022-11-10T19:35:26.567880Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_path(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:26.570753Z","iopub.execute_input":"2022-11-10T19:35:26.571077Z","iopub.status.idle":"2022-11-10T19:35:26.656549Z","shell.execute_reply.started":"2022-11-10T19:35:26.571048Z","shell.execute_reply":"2022-11-10T19:35:26.655519Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:26.658513Z","iopub.execute_input":"2022-11-10T19:35:26.658918Z","iopub.status.idle":"2022-11-10T19:35:26.698926Z","shell.execute_reply.started":"2022-11-10T19:35:26.658880Z","shell.execute_reply":"2022-11-10T19:35:26.697829Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_peak_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:26.700986Z","iopub.execute_input":"2022-11-10T19:35:26.701448Z","iopub.status.idle":"2022-11-10T19:35:26.709770Z","shell.execute_reply.started":"2022-11-10T19:35:26.701405Z","shell.execute_reply":"2022-11-10T19:35:26.708539Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_acceleration(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:26.711920Z","iopub.execute_input":"2022-11-10T19:35:26.712555Z","iopub.status.idle":"2022-11-10T19:35:26.753296Z","shell.execute_reply.started":"2022-11-10T19:35:26.712494Z","shell.execute_reply":"2022-11-10T19:35:26.752196Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:26.754859Z","iopub.execute_input":"2022-11-10T19:35:26.755254Z","iopub.status.idle":"2022-11-10T19:35:26.832037Z","shell.execute_reply.started":"2022-11-10T19:35:26.755222Z","shell.execute_reply":"2022-11-10T19:35:26.830982Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:26.833840Z","iopub.execute_input":"2022-11-10T19:35:26.834231Z","iopub.status.idle":"2022-11-10T19:35:26.842041Z","shell.execute_reply.started":"2022-11-10T19:35:26.834200Z","shell.execute_reply":"2022-11-10T19:35:26.840910Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cat = 8","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:26.844372Z","iopub.execute_input":"2022-11-10T19:35:26.844712Z","iopub.status.idle":"2022-11-10T19:35:26.851851Z","shell.execute_reply.started":"2022-11-10T19:35:26.844683Z","shell.execute_reply":"2022-11-10T19:35:26.850891Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display(HTML(title_texts[cat]))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:26.853182Z","iopub.execute_input":"2022-11-10T19:35:26.853491Z","iopub.status.idle":"2022-11-10T19:35:26.864719Z","shell.execute_reply.started":"2022-11-10T19:35:26.853456Z","shell.execute_reply":"2022-11-10T19:35:26.863988Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"category_df = category_dfs[cat][\"df\"]\n\nagg_df = category_df.groupby('seconds')[['latitude', 'longitude', 'velocity', 'acceleration']].mean().reset_index(level=0)\nweight_df = category_df.groupby('racer_id')['weight_carried'].first().to_frame()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:26.866421Z","iopub.execute_input":"2022-11-10T19:35:26.867498Z","iopub.status.idle":"2022-11-10T19:35:26.880500Z","shell.execute_reply.started":"2022-11-10T19:35:26.867402Z","shell.execute_reply":"2022-11-10T19:35:26.879200Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_path(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:26.882144Z","iopub.execute_input":"2022-11-10T19:35:26.883292Z","iopub.status.idle":"2022-11-10T19:35:26.967972Z","shell.execute_reply.started":"2022-11-10T19:35:26.883254Z","shell.execute_reply":"2022-11-10T19:35:26.966865Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:26.969663Z","iopub.execute_input":"2022-11-10T19:35:26.970480Z","iopub.status.idle":"2022-11-10T19:35:27.008101Z","shell.execute_reply.started":"2022-11-10T19:35:26.970445Z","shell.execute_reply":"2022-11-10T19:35:27.006902Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_peak_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.010105Z","iopub.execute_input":"2022-11-10T19:35:27.010545Z","iopub.status.idle":"2022-11-10T19:35:27.018255Z","shell.execute_reply.started":"2022-11-10T19:35:27.010503Z","shell.execute_reply":"2022-11-10T19:35:27.017193Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_acceleration(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.019532Z","iopub.execute_input":"2022-11-10T19:35:27.019829Z","iopub.status.idle":"2022-11-10T19:35:27.061552Z","shell.execute_reply.started":"2022-11-10T19:35:27.019802Z","shell.execute_reply":"2022-11-10T19:35:27.060444Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.063157Z","iopub.execute_input":"2022-11-10T19:35:27.063456Z","iopub.status.idle":"2022-11-10T19:35:27.140482Z","shell.execute_reply.started":"2022-11-10T19:35:27.063429Z","shell.execute_reply":"2022-11-10T19:35:27.139313Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.142580Z","iopub.execute_input":"2022-11-10T19:35:27.143121Z","iopub.status.idle":"2022-11-10T19:35:27.151163Z","shell.execute_reply.started":"2022-11-10T19:35:27.143079Z","shell.execute_reply":"2022-11-10T19:35:27.149995Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cat = 9","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.152466Z","iopub.execute_input":"2022-11-10T19:35:27.152758Z","iopub.status.idle":"2022-11-10T19:35:27.160002Z","shell.execute_reply.started":"2022-11-10T19:35:27.152730Z","shell.execute_reply":"2022-11-10T19:35:27.158752Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display(HTML(title_texts[cat]))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.162108Z","iopub.execute_input":"2022-11-10T19:35:27.162607Z","iopub.status.idle":"2022-11-10T19:35:27.172017Z","shell.execute_reply.started":"2022-11-10T19:35:27.162561Z","shell.execute_reply":"2022-11-10T19:35:27.170695Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"category_df = category_dfs[cat][\"df\"]\n\nagg_df = category_df.groupby('seconds')[['latitude', 'longitude', 'velocity', 'acceleration']].mean().reset_index(level=0)\nweight_df = category_df.groupby('racer_id')['weight_carried'].first().to_frame()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.174124Z","iopub.execute_input":"2022-11-10T19:35:27.174620Z","iopub.status.idle":"2022-11-10T19:35:27.187552Z","shell.execute_reply.started":"2022-11-10T19:35:27.174576Z","shell.execute_reply":"2022-11-10T19:35:27.186383Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_path(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.189328Z","iopub.execute_input":"2022-11-10T19:35:27.189899Z","iopub.status.idle":"2022-11-10T19:35:27.276735Z","shell.execute_reply.started":"2022-11-10T19:35:27.189856Z","shell.execute_reply":"2022-11-10T19:35:27.275606Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.287497Z","iopub.execute_input":"2022-11-10T19:35:27.287911Z","iopub.status.idle":"2022-11-10T19:35:27.327988Z","shell.execute_reply.started":"2022-11-10T19:35:27.287874Z","shell.execute_reply":"2022-11-10T19:35:27.326915Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_peak_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.329371Z","iopub.execute_input":"2022-11-10T19:35:27.329699Z","iopub.status.idle":"2022-11-10T19:35:27.337427Z","shell.execute_reply.started":"2022-11-10T19:35:27.329670Z","shell.execute_reply":"2022-11-10T19:35:27.336398Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_acceleration(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.339143Z","iopub.execute_input":"2022-11-10T19:35:27.339570Z","iopub.status.idle":"2022-11-10T19:35:27.384354Z","shell.execute_reply.started":"2022-11-10T19:35:27.339540Z","shell.execute_reply":"2022-11-10T19:35:27.383445Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.385792Z","iopub.execute_input":"2022-11-10T19:35:27.386363Z","iopub.status.idle":"2022-11-10T19:35:27.464205Z","shell.execute_reply.started":"2022-11-10T19:35:27.386329Z","shell.execute_reply":"2022-11-10T19:35:27.463023Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.465871Z","iopub.execute_input":"2022-11-10T19:35:27.466273Z","iopub.status.idle":"2022-11-10T19:35:27.474371Z","shell.execute_reply.started":"2022-11-10T19:35:27.466239Z","shell.execute_reply":"2022-11-10T19:35:27.473242Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cat = 10","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.476448Z","iopub.execute_input":"2022-11-10T19:35:27.476907Z","iopub.status.idle":"2022-11-10T19:35:27.485258Z","shell.execute_reply.started":"2022-11-10T19:35:27.476864Z","shell.execute_reply":"2022-11-10T19:35:27.484144Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display(HTML(title_texts[cat]))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.487088Z","iopub.execute_input":"2022-11-10T19:35:27.487548Z","iopub.status.idle":"2022-11-10T19:35:27.498203Z","shell.execute_reply.started":"2022-11-10T19:35:27.487504Z","shell.execute_reply":"2022-11-10T19:35:27.496929Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"category_df = category_dfs[cat][\"df\"]\n\nagg_df = category_df.groupby('seconds')[['latitude', 'longitude', 'velocity', 'acceleration']].mean().reset_index(level=0)\nweight_df = category_df.groupby('racer_id')['weight_carried'].first().to_frame()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.500592Z","iopub.execute_input":"2022-11-10T19:35:27.501165Z","iopub.status.idle":"2022-11-10T19:35:27.513800Z","shell.execute_reply.started":"2022-11-10T19:35:27.501118Z","shell.execute_reply":"2022-11-10T19:35:27.512756Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_path(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.515373Z","iopub.execute_input":"2022-11-10T19:35:27.515791Z","iopub.status.idle":"2022-11-10T19:35:27.605272Z","shell.execute_reply.started":"2022-11-10T19:35:27.515761Z","shell.execute_reply":"2022-11-10T19:35:27.604309Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.609067Z","iopub.execute_input":"2022-11-10T19:35:27.609405Z","iopub.status.idle":"2022-11-10T19:35:27.652902Z","shell.execute_reply.started":"2022-11-10T19:35:27.609376Z","shell.execute_reply":"2022-11-10T19:35:27.651903Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_peak_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.654804Z","iopub.execute_input":"2022-11-10T19:35:27.655265Z","iopub.status.idle":"2022-11-10T19:35:27.664461Z","shell.execute_reply.started":"2022-11-10T19:35:27.655221Z","shell.execute_reply":"2022-11-10T19:35:27.663247Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_acceleration(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.666883Z","iopub.execute_input":"2022-11-10T19:35:27.667251Z","iopub.status.idle":"2022-11-10T19:35:27.706158Z","shell.execute_reply.started":"2022-11-10T19:35:27.667218Z","shell.execute_reply":"2022-11-10T19:35:27.705057Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.708140Z","iopub.execute_input":"2022-11-10T19:35:27.708601Z","iopub.status.idle":"2022-11-10T19:35:27.791974Z","shell.execute_reply.started":"2022-11-10T19:35:27.708546Z","shell.execute_reply":"2022-11-10T19:35:27.790863Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.794200Z","iopub.execute_input":"2022-11-10T19:35:27.795069Z","iopub.status.idle":"2022-11-10T19:35:27.803050Z","shell.execute_reply.started":"2022-11-10T19:35:27.795023Z","shell.execute_reply":"2022-11-10T19:35:27.801931Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cat = 11","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.807225Z","iopub.execute_input":"2022-11-10T19:35:27.807582Z","iopub.status.idle":"2022-11-10T19:35:27.815573Z","shell.execute_reply.started":"2022-11-10T19:35:27.807552Z","shell.execute_reply":"2022-11-10T19:35:27.814327Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display(HTML(title_texts[cat]))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.817680Z","iopub.execute_input":"2022-11-10T19:35:27.818196Z","iopub.status.idle":"2022-11-10T19:35:27.828019Z","shell.execute_reply.started":"2022-11-10T19:35:27.818150Z","shell.execute_reply":"2022-11-10T19:35:27.826997Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"category_df = category_dfs[cat][\"df\"]\n\nagg_df = category_df.groupby('seconds')[['latitude', 'longitude', 'velocity', 'acceleration']].mean().reset_index(level=0)\nweight_df = category_df.groupby('racer_id')['weight_carried'].first().to_frame()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.830177Z","iopub.execute_input":"2022-11-10T19:35:27.830919Z","iopub.status.idle":"2022-11-10T19:35:27.844513Z","shell.execute_reply.started":"2022-11-10T19:35:27.830875Z","shell.execute_reply":"2022-11-10T19:35:27.843521Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_path(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.846555Z","iopub.execute_input":"2022-11-10T19:35:27.847032Z","iopub.status.idle":"2022-11-10T19:35:27.939690Z","shell.execute_reply.started":"2022-11-10T19:35:27.846978Z","shell.execute_reply":"2022-11-10T19:35:27.938557Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.941517Z","iopub.execute_input":"2022-11-10T19:35:27.941994Z","iopub.status.idle":"2022-11-10T19:35:27.982235Z","shell.execute_reply.started":"2022-11-10T19:35:27.941929Z","shell.execute_reply":"2022-11-10T19:35:27.981040Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_peak_velocity(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.984074Z","iopub.execute_input":"2022-11-10T19:35:27.984573Z","iopub.status.idle":"2022-11-10T19:35:27.992585Z","shell.execute_reply.started":"2022-11-10T19:35:27.984530Z","shell.execute_reply":"2022-11-10T19:35:27.991398Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_acceleration(agg_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:27.994152Z","iopub.execute_input":"2022-11-10T19:35:27.994506Z","iopub.status.idle":"2022-11-10T19:35:28.036782Z","shell.execute_reply.started":"2022-11-10T19:35:27.994474Z","shell.execute_reply":"2022-11-10T19:35:28.035681Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:28.038960Z","iopub.execute_input":"2022-11-10T19:35:28.039436Z","iopub.status.idle":"2022-11-10T19:35:28.116949Z","shell.execute_reply.started":"2022-11-10T19:35:28.039392Z","shell.execute_reply":"2022-11-10T19:35:28.115843Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print_weight(weight_df)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-10T19:35:28.118439Z","iopub.execute_input":"2022-11-10T19:35:28.118782Z","iopub.status.idle":"2022-11-10T19:35:28.125922Z","shell.execute_reply.started":"2022-11-10T19:35:28.118752Z","shell.execute_reply":"2022-11-10T19:35:28.124945Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 7. Conclusion","metadata":{}},{"cell_type":"markdown","source":"The approach we have taken has tried to decouple jockey and horse performance from qualitative characteristcs, while concentrating on quantitative characteristcs that can be generalized to any jockey or horse.
\nWe've chosen our 12 categories setting a minimum number of sample races within the categories to 12.
\nMore sample races in the future will lead to more categories we can study statistically.","metadata":{}},{"cell_type":"markdown","source":"To get even more insight, one exploration vertical might be to track biometric data for both horse and jockeys (e.g. heart rate evolution during the race).
\nThat way we might be able to draft strategies that more accurately keep jockey and horse health into account.","metadata":{}}]}