Exploratory Data Analysis Cheat Sheet

import pandas as pddf = pd.read_csv("data.csv")df.shape                        # (rows, columns)df.info()                       # dtypes, non-null counts, memory usagedf.describe()                   # count, mean, std, min, quartiles, max for numeric colsdf.describe(include="object")   # summary for categorical columnsdf.head()df.isnull().sum()df.nunique()                    # unique value counts per columndf["category"].value_counts(normalize=True)  # class proportions

import seaborn as snsimport matplotlib.pyplot as plt# Distribution of a numeric variablesns.histplot(df["income"], kde=True, bins=30)# Boxplot to spot outliers/spread by categorysns.boxplot(x="category", y="income", data=df)# Correlation heatmapcorr = df.corr(numeric_only=True)sns.heatmap(corr, annot=True, cmap="coolwarm", center=0)# Pairwise relationships between numeric featuressns.pairplot(df, hue="target", vars=["age", "income", "score"])plt.tight_layout()plt.show()