aqd14

Notes

column 0 = year, column 1 = month, column 2 = day
data = pd.read_csv('./wind.data', sep='\s+', parse_dates=[[0, 1, 2]])

aqd14

Notes

df.drop[['unselected_columns'], axis=1]

aqd14

Notes

Calculate the ratio of male grouped by occupation

occupation_grouped = users.groupby('occupation')

# Get back a multiindex pandas' Series containing ratio 
# for each gender in each occupation

aqd14

Notes

// Assume we have a 'gender' column with only M and F values
// solution 1
users['gender_n'] = [1 if gender == 'M' else 0 for gender in users['gender']]

// solution 2
users['gender_n'] = np.where(users['gender'] == 'M', 1, 0)

aqd14

Notes

# rename column by passing tuples
grouped_pct.agg([('foo', 'mean'), ('bar', np.std)])

aqd14

## Problem 1.1
### You have an N-element tuple or sequence that you would like to unpack into a collection of N variables.
```
p = (4, 5)
x, y = p # x = 4, y = 5
```

## Problem 1.2
#### You need to unpack N elements from an iterable, but the iterable may be longer than N elements, causing a “too many values to unpack” exception.

aqd14

# Defining and initializing vectors

vector<T> v1; // vector that holds object of type T, default constructor v1 is empty

vector<T> v2 (v1); // v2 is a copy of v1

vector<T> v3(n, i); // v2 has n elements with value i

vector<T> v4(n); // v4 has n copies of a value-initialized object

aqd14

college_data_processed <- college_data_processed %>%
    group_by(STATENAME) %>%
    mutate_at(vars(-UNITID:-REGION, -INSTNM), ~ifelse(is.na(.x), mean(.x, na.rm = TRUE), .x))

aqd14

# Notes

grand_slam_ages <- player_dob %>%
    select(name, date_of_birth) %>%
    inner_join(grand_slams, by = "name") %>%
    mutate(age = as.numeric(difftime(tournament_date, date_of_birth, unit = "days") / 365.25))

aqd14

grand_slam_ages %>%
    mutate(decade = 10 * (year %/% 10)) %>%
    ggplot(aes(decade, age, fill = gender, group = interaction(decade, gender))) +
    geom_boxplot() +
    scale_x_continuous(breaks = seq(1950, 2021, 10)) +
    expand_limits(x = 2020)