Python Environment

# Install a package
!pip install package-name

# Install a specific version
!pip install package-name==1.2.3

# Install multiple packages
!pip install package1 package2 package3

# NLP
!pip install nltk spacy transformers

# Time series
!pip install prophet pmdarima

# Geographic
!pip install geopandas folium

# Financial
!pip install yfinance pandas-ta

# Parquet is faster than CSV for large files
df = pd.read_parquet('large_file.parquet')

# Or use Polars for even better performance
import polars as pl
df = pl.read_parquet('large_file.parquet')

# Chunked reading for huge CSVs
chunks = pd.read_csv('huge.csv', chunksize=10000)
for chunk in chunks:
    process(chunk)

# Check memory usage
import sys
print(f"DataFrame size: {df.memory_usage(deep=True).sum() / 1e6:.1f} MB")

# Free memory by deleting large objects
del large_dataframe
import gc
gc.collect()

# Use efficient dtypes
df['category_col'] = df['category_col'].astype('category')
df['small_int'] = df['small_int'].astype('int8')

# Pandas display options
pd.set_option('display.max_columns', 50)
pd.set_option('display.max_rows', 100)
pd.set_option('display.float_format', '{:.2f}'.format)

# Matplotlib defaults
plt.rcParams['figure.figsize'] = [10, 6]
plt.rcParams['figure.dpi'] = 100

# Plotly defaults (for inline display)
import plotly.io as pio
pio.renderers.default = 'notebook'