Describe the primary objectives of Exploratory Data Analysis (EDA), and outline the key visualizations and statistical summaries you would perform on a new dataset.

Exploratory Data Analysis (EDA) is a critical initial step in any data science project. It involves using statistical techniques and visualizations to summarize, analyze, and gain a deeper understanding of the dataset before any modeling or formal analysis is performed. The primary objectives of EDA are to: 1. Understand the Data Structure: EDA helps to determine the structure of the data, including the number of observations (rows) and variables (columns), the type of data in each column (numerical, categorical, or textual), and the presence of missing values. This provides the basic blueprint of what you're working with and highlights data quality concerns to be addressed in preprocessing. For example, knowing a dataset has 1000 rows and 20 columns with a mix of integers and floating point numbers, and several text based columns helps the data scientist understand the initial information on hand. 2. Identify Data Quality Issues: EDA is crucial for detecting issues like missing data, incorrect values, outliers, and inconsistencies. By finding these issues early, they can be addressed before they have a significant impact on later analysis or modeling. For example, plotting histograms of numeric data can reveal unusual patterns or spikes, signaling erroneous data values. A dataset of temperatures might show some values that are clearly incorrect if they are way outside of the reasonable bounds. 3. Discover Patterns, Trends, and Relationships: EDA is instrumental in uncovering patterns, trends, and relationships between variables. These insights might be apparent in the form of trends in time series data, correlations between different features, or even unexpected groupings within the data, which are crucial to understand the context of the data. For example, visualizing a scatter plot of age versus income might reveal patterns, such as older people generally earning more income, or might show that there is not much of a relationship between the features. 4. Formulate Hypotheses and Research Questions: EDA can ....