pandas

 dataframe

Two-dimensional, size-mutable, potentially heterogeneous tabular data.

 class pandas.DataFrame(data=None, index=None, columns=None, dtype=None, copy=None)

 

 

import pandas as pd

import numpy as np

 

colab example

https://colab.research.google.com/github/google/eng-edu/blob/main/ml/cc/exercises/pandas_dataframe_ultraquick_tutorial.ipynb

# Create and populate a 5x2 NumPy array.

my_data = np.array([[0, 3], [10, 7], [20, 9], [30, 14], [40, 15]])

# Create a Python list that holds the names of the two columns.

my_column_names = ['temperature', 'activity']

# Create a DataFrame.

my_dataframe = pd.DataFrame(data=my_data, columns=my_column_names)

# Print the entire DataFrame

print(my_dataframe)

 

# Create a new column named adjusted.

my_dataframe["adjusted"] = my_dataframe["activity"] + 2

# Print the entire DataFrame

print(my_dataframe)

 

print("Rows #0, #1, and #2:")

print(my_dataframe.head(3), '\n')

print("Row #2:")

print(my_dataframe.iloc[[2]], '\n')

print("Rows #1, #2, and #3:")

print(my_dataframe[1:4], '\n')

print("Column 'temperature':")

print(my_dataframe['temperature'])

 

# Create a reference by assigning my_dataframe to a new variable.

print("Experiment with a reference:")

reference_to_df = df

# Print the starting value of a particular cell.

print(" Starting value of df: %d" % df['Jason'][1])

print(" Starting value of reference_to_df: %d\n" % reference_to_df['Jason'][1])

# Modify a cell in df.

df.at[1, 'Jason'] = df['Jason'][1] + 5

print(" Updated df: %d" % df['Jason'][1])

print(" Updated reference_to_df: %d\n\n" % reference_to_df['Jason'][1])

# Create a true copy of my_dataframe

print("Experiment with a true copy:")

copy_of_my_dataframe = my_dataframe.copy()

# Print the starting value of a particular cell.

print(" Starting value of my_dataframe: %d" % my_dataframe['activity'][1])

print(" Starting value of copy_of_my_dataframe: %d\n" % copy_of_my_dataframe['activity'][1])

# Modify a cell in df.

my_dataframe.at[1, 'activity'] = my_dataframe['activity'][1] + 3

print(" Updated my_dataframe: %d" % my_dataframe['activity'][1])

print(" copy_of_my_dataframe does not get updated: %d" % copy_of_my_dataframe['activity'][1])

 

 

d = {'col1': [1, 2], 'col2': [3, 4]}

df = pd.DataFrame(data=d)

df
   col1  col2
0     1     3
1     2     4 

df.dtypes
col1    int64
col2    int64
dtype: object

To enforce a single dtype:

df = pd.DataFrame(data=d, dtype=np.int8)

https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.html