Data science lifecycle Tabular dataset Target variable Feature matrix Train validation test split Data dictionary Reproducible random seed Notebook versus script Data provenance Experiment tracking

NumPy array creation Array shape Array dtype Array slicing Boolean masking Broadcasting Vectorized arithmetic Aggregation reshape Matrix multiplication

DataFrame creation Read CSV Select columns Filter rows sort_values groupby merge pivot_table set_index Missing values

Drop duplicates Fill missing numeric values Fill missing categorical values Parse dates String cleanup Outlier detection IQR Type conversion Category dtype Rename columns Validate ranges

Descriptive statistics Mean median mode Variance standard deviation Quantiles Correlation Frequency table Crosstab Histogram Box plot Scatter plot

Matplotlib line chart Matplotlib bar chart Matplotlib labels Multiple series Seaborn concept without dependency Plot distribution Plot correlation matrix Time-series plot Save figure Accessible chart labels

One-hot encoding Ordinal encoding Standard scaling Min max scaling Log transform Polynomial features Date parts Text length feature Interaction feature Pipeline concept

Linear regression Logistic regression Decision tree concept K nearest neighbors K means clustering Confusion matrix Precision recall Cross validation Baseline model Model persistence