Please enable JavaScript.
Coggle requires JavaScript to display documents.
Exploratory Data Analysis (EDA) - Coggle Diagram
Exploratory Data Analysis (EDA)
Retrieving data
pd.read_csv(filename)
File
CSV
JSON
Excel
Database
API
Cleaning Messy Data
Duplicates or unnecessary data
Inconsistent text and typos
Missing data
Remove row(s)
Impute
Replace with substitued/estimated values
Mask
Create category for missing values
Outliers
Detection
Plots
Histogram
Density plot
Box plot
Stats
Interquartile range
Standard deviation
Residuals
Standardized
Deleted
Studentized
Policies
Remove
Assign
mean or median
Transform
e.g. log transformation
Predict
using similar observations
using regression
Keep
Data sourcing
On-prem and/or in cloud
Different database types
Multiple systems
Sample data using Pandas