Image by Pexels from Pixabay

Creating data frames using pandas library

Data frame is a collection of series.

Creating a data frame by combining series

#Import pandas library
import pandas as pd
#Creating first series
price_series_1 = pd.Series(data = [10, 15, 30, 9, 20, 10], index=['apple', 'banana', 'orange', 'grape', 'mango', 'lime'])
#Creating second series
sales_series_2 = pd.Series(data = [5, 10, 20, 90, 25], index=['apple', 'banana', 'orange', 'grape', 'mango'])
#axis = 1 will create multiple columns
#sort = True will sort by row index names
fruit_data_frame_1 = pd.concat([price_series_1, sales_series_2], axis=1, sort=False)
print(fruit_data_frame_1)
         0     1
apple   10   5.0
banana  15  10.0
orange  30  20.0
grape    9  90.0
mango   20  25.0
lime    10   NaN
#axis=0 will stack the series on top
fruit_data_frame_1 = pd.concat([price_series_1, sales_series_2], axis=0, sort=False)
print(fruit_data_frame_1)
apple     10
banana    15
orange    30
grape      9
mango     20
lime      10
apple      5
banana    10
orange    20
grape     90
mango     25
dtype: int64

Creating from a NumPy matrix

import pandas as pd
import numpy as np
#Creating from a random 3X3 matrix
data_frame_1 = pd.DataFrame(np.random.randn(3, 3))
print(data_frame_1)
          0          1          2
0  0.060806  -0.806543   0.859473
1 -0.136783  -0.711317  -0.101713
2 -0.259168   0.362533   0.080274
#Assigning row and column names
data_frame_2=pd.DataFrame(np.random.randn(3, 3), index=['row1', 'row2', 'row3'], columns=['col1', 'col2', 'col3'])
print(data_frame_2)
          col1      col2      col3
row1 -0.283342 -0.307254  0.246655
row2 -1.157004  0.376876  0.355617
row3  0.512803  0.657995  0.413148

Creating from a python dictionary and writing to csv

import pandas as pd
#Python dictionary
mydict = {'price': [100, 200, 300, 400],
         'sales': [10, 20, 30, 40]}
labels = ['apple', 'banana', 'orange', 'grape']
data_frame_3 = pd.DataFrame(mydict, index=labels)
print(data_frame_3)
        price  sales
apple     100     10
banana    200     20
orange    300     30
grape     400     40
#Writing to a csv
data_frame_3.to_csv('fruit_sales.csv')

Creating from a CSV file

My CSV file contains below data

import pandas as pd
#Loading from csv
data_frame_5 = pd.read_csv('fruit_sales.csv', index_col=0)
#index_col = 0 says that the first column 'A' is index value.
print(data_frame_5)
        price  sales
apple     100     10
banana    200     20
orange    300     30
grape     400     40