reference/datanalysisref.txt

# read data file in R
df = data.table::fread('/path/to/file.csv')

# read data file in Python
df = pd.read_csv('/path/to/file.csv')

# list column names in R
names(df)
colnames(df)

# list column names in Python
df.columns

# list row names in R
rownames(df)

# list row names in Python
df.index

# list number of columns in R
ncol(df)

# list number of rows in R
nrow(df)

# list dimensions of dataframe in R
dim(df)

# list dimensions of dataframe in Python
df.shape

# access a column of a dataframe in Python
df['colname'].head(4)

# access a row of a dataframe in Python
df.loc[3].head(4)
df.iloc[3].head(4)

# list first/last n rows of a dataframe in R
head(df, n)
tail(df, n)

# list first/last n rows of a dataframe in Python
df.head(n)
df.tail(n)

# describe dataframe in R
summary(df)

# describe dataframe in Python
df.describe()

# data types of attributes in Python
df.info()

# correlation of attributes in the data
df.corr(method='pearson')