# Visualize sampling distribution

df_sample = df.sample(n=10)

df_sample["col"].hist(bins=np.arange(59, 93, 2))

plt.show()

# Sampling with replacement (for dependent event)

df["col"].sample(5, replace = True)

# Sampling without replacement (for independent event)

df["col"].sample(5, replace = False)

​

# Simple random sampling

simple_sample = df.sample(n=5, random_state=42)

​

# Systematic sampling

sample_size = 5

pop_size = len(df)

interval = pop_size // sample_size

shuffled_df = df.sample(frac=1)

shuffled_df = shuffled_df.reset_index(drop=True).reset_index()

systematic_sample = shuffled_df.iloc[::interval]

​

# Stratified sampling

prop_stratified_sample = df.groupby("cat_col").sample(frac=0.1, random_state=42)

equal_stratified_sample = df.groupby("cat_col").sample(n=15, random_state=42)

​

# Weighted sampling

condition = df['cat_col'] == "Val"

df['weight'] = np.where(condition, 2, 1)

weighted_sample = df.sample(frac=0.1, weights="weight")

​

# Cluster sampling

category_list = list(df['cat_col'].unique())

import random

random_categories = random.sample(category_list, k=3)

subset_rows = df['cat_col'].isin(random_categories)

subset_df = df[subset_rows]

subset_df['cat_col'] = subset_df['cat_col'].cat.remove_unused_categories()

sample_cluster = subset_df.groupby("cat_col").sample(n=5, random_state=42)

​

# Visualize to make sure white noise so that sampling is random

sample_df.plot(x="col1", y="col2", kind="scatter")

plt.show()