Exam 2 Solutions

import pandas as pa

df = pa.read_csv('https://raw.githubusercontent.com/nurfnick/Data_Viz/main/Activity_Dataset_V1.csv')

df.dtypes

Unnamed: 0          int64
activity_day       object
workout_type       object
distance          float64
time                int64
calories            int64
total_steps       float64
avg_speed         float64
avg_cadence       float64
max_cadence       float64
avg_pace           object
max_pace           object
min_pace           object
avg_heart_rate    float64
max_heart_rate    float64
min_heart_rate      int64
vo2_max(%)          int64
aerobic(%)          int64
anaerobic(%)        int64
intensive(%)        int64
light(%)            int64
dtype: object

df = df.drop('Unnamed: 0', axis = 1)

df.head()

	activity_day	workout_type	distance	time	calories	total_steps	avg_speed	avg_cadence	max_cadence	avg_pace	max_pace	min_pace	avg_heart_rate	max_heart_rate	min_heart_rate	vo2_max(%)	aerobic(%)	anaerobic(%)	intensive(%)	light(%)
0	2022-01-01	Freestyle	9.30	77	123	NaN	18.88	168.54	138.30	NaN	NaN	NaN	112.5	122.0	103	19	28	2	7	50
1	2022-01-01	Freestyle	3.44	96	55	NaN	29.65	125.92	292.81	NaN	NaN	NaN	111.0	122.0	100	42	28	2	29	88
2	2022-01-01	Indoor Cycling	6.34	85	33	NaN	17.85	81.93	323.69	NaN	NaN	NaN	95.0	90.0	100	1	32	0	22	43
3	2022-01-01	Walking	7.91	42	82	1571.0	22.10	29.63	180.16	07:58	28:58	07:58	83.0	85.0	81	3	22	0	24	65
4	2022-01-01	Open Water	8.99	36	131	NaN	25.83	64.55	342.89	NaN	NaN	NaN	138.0	166.0	110	7	0	5	21	88

import re
newcol = []
for col in df.columns:
  newcol.append(re.sub(r'\(%\)',"",col))

df.columns = newcol

df.columns

Index(['activity_day', 'workout_type', 'distance', 'time', 'calories',
       'total_steps', 'avg_speed', 'avg_cadence', 'max_cadence', 'avg_pace',
       'max_pace', 'min_pace', 'avg_heart_rate', 'max_heart_rate',
       'min_heart_rate', 'vo2_max', 'aerobic', 'anaerobic', 'intensive',
       'light'],
      dtype='object')

df.activity_day = pa.to_datetime(df.activity_day)

df.total_steps = df.total_steps.fillna(0)

df.avg_pace = df.avg_pace.fillna('00:00').apply(lambda s: int(s[0:2])+int(s[3:6])/60 )

df.groupby('workout_type').calories.agg(['mean', 'median','std','count'])

	mean	median	std	count
workout_type
Cricket	307.548387	330.0	149.950609	93
Freestyle	278.552083	294.0	163.703768	96
Indoor Cycling	280.450000	306.0	156.633322	80
Open Water	296.747253	328.0	160.068499	91
Outdoor Cycling	299.129412	301.0	158.731263	85
Outdoor Running	301.469136	349.0	165.725080	81
Pool Swimming	283.414894	300.0	157.576703	94
Trail Run	267.966667	264.0	155.748533	90
Treadmill	278.142857	269.5	146.963352	98
Trekking	283.127660	280.5	151.034870	94
Walking	276.040816	270.5	157.287570	98

df['high_aerobic'] = df.aerobic >0.3

where = df[df.max_cadence == max(df.max_cadence)].workout_type.item()

when = df[df.max_cadence == max(df.max_cadence)].activity_day.dt.day_name().item()

print('The max cadence happened on {} in the {}'.format(when,where))

The max cadence happened on Wednesday in the Pool Swimming