Pandas

pd.Series

# constructor
pd.Series([1, 2, 3, 4, 5])
pd.Series([30, 35, 40], index=['2015 Sales', '2016 Sales', '2017 Sales'], name='Product A')

boolean operations

# s1, s2 are series with dtype: bool
s1 | s2 # or
s1 & s2 # and

pd.Series.describe()

It is type-aware, meaning that its output changes based on the data type of the input.

other operations

s.mean()
s.unique()
s.value_counts()

pd.DataFrame

# constructor
pd.DataFrame({'my-column-1': [50, 21], 'my-column-2': [131, 2]})
pd.DataFrame({'my-column-1': [50, 21], 'my-column-2': [131, 2]}, index=['my-index-1', 'my-index-2'])

# count rows
len(df)

get column

# access column
# all are equivalent
df.column_name
df['column_name']
df.loc[:, 'column_name']

set column

# assign fixed value to column
df.column_name = 'fixed_value'

# assign any iterable to column
# length of iterable must match length of `df`
df.column_name = range(len(df), 0, -1)

get pd.Series with dtype: bool

# true if value null / not null respectively
df.column_name.isnull()
df.column_name.notnull()

# true if value is among the collection
df.column_name.isin(['value_1', 'value_8', 'value_3'])

other operations

df.shape
df.head()
df.describe()
pd.set_option('display.max_rows', 500)
pd.set_option('display.max_columns', 500)
pd.set_option('display.width', 1000)
reviews.set_index('column_name') # assign column as index

Others

df = pd.read_csv("../data/data.csv")
df = pd.read_csv("../data/data.csv", index_col=0) # if index is part of csv