2020.01.01.(pm): Statistical analysis using pandas

1. pandas features

pandas has the following characteristics:

• Easy handling of missing values
• Create data with automatic and explicit label position
• Data-intensive
• Advanced label-based slicing, extraction, and subset of large datasets
• Intuitive Dataset Combination
• Flexible transformation and transformation of datasets
• Descriptive labeling of axes
• Powerful I / O corresponding to various data formats
• Inherent Processing of Time Series Data

To create a Series, use the pandas .series class. The first argument is passed one-dimensional data as follows.

• list
• tuple
• dictionary
• numpy.ndarray

exclude index

Let’s load the anime_master.csv data in sample-data. At first, I had some trouble because I couldn’t set the path properly.

2. Visualize sample data

full code and content:
https://github.com/SeongjooHong/jupyter-notebook/blob/master/pandas%202.ipynb