pandas_cheatsheet.txt

# Pandas usage
import pandas as pd
...

# SERIES
# https://pandas.pydata.org/pandas-docs/stable/dsintro.html?highlight=series
# Attributes:- 
s.name 
# Methods: -
s.rename('something') --> rename name
# Create a series
s2 = pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd'])

# Create series from dictionary
s2 = pd.Series({'a': 1, 'b': 2, 'c': 3, 'd': 4, 'e': 5})

# Number of elements:- 
len(s)

# Some functions:-
s.shape
s.count()
s.unique()
s.value_counts()
s.index
s.values

Access element:-
s.loc[index]

# DATAFRAME
# Creation:-
1) From Numpy array
pd.DataFrame(np.array([[10, 11], [20, 21]]))

2) From Series
df1 = pd.DataFrame([pd.Series(np.arange(10, 15)), 
                       pd.Series(np.arange(15, 20))])

3) Specify columns in Constructor.
df = pd.DataFrame(np.array([[10, 11], [20, 21]]), 
                     columns=['a', 'b'])

# Some functions
df.columns
df.index
df.values

# Drop columns
df.drop(['A', 'B'], axis = 1, inplace = True)

# Print column names of a pandas dataframe 
print(df.columns)

# Rename Columns
df.rename(columns={'oldName1': 'newName1', 'oldName2': 'newName2'}, inplace=True)

# Convert rows to columns
df = df.transpose()

# Select a column
ohlc_df = df[['ohlc']]

# Set index 
df.set_index('<index name>',inplace=True)

# Select a row
s = ohlc_df.iloc[0]
Returns a pandas.Series object
pandas.Series:- consists of an index and a sequence of values

# Insert a row
df.loc[1] = ['a', 'b', 'c']

# Insert rows from lists
df.loc['indexname'] = 
# https://www.shanelynn.ie/select-pandas-dataframe-rows-and-columns-using-iloc-loc-and-ix/

# Put single value at passed column and index
DataFrame.set_value(index, col, value, takeable=False)

Parameters:	
index : row label
col : column label
value : scalar value
takeable : interpret the index/col as indexers, default False
Returns:	
frame : DataFrame
If label pair is contained, will be reference to calling DataFrame, otherwise a new object

# Get the index of a row.
index = df.iloc[-1].name

# How a make a list out of column.
dfList = df['one'].tolist()

# Query a dataframe
df[df['A'].str.contains("hello")]
df.loc[df['column_name'] == some_value]
df.loc[df['column_name'].isin(some_values)]
df.loc[(df['column_name'] == some_value) & df['other_column'].isin(some_values)]
df.loc[df['column_name'] != some_value]
df.loc[~df['column_name'].isin(some_values)]


# Numpy array from dataframe
np_array = df.iloc[:, 1:2].values