Pandas / Matplotlib Goodies

goodies.py

# Creating a new plot with no spacing

fig, axes = plt.subplots(2, 2, sharex=True, sharey=True) for i in range(2):
for j in range(2):
axes[i, j].hist(randn(500), bins=50, color='k', alpha=0.5)
plt.subplots_adjust(wspace=0, hspace=0)

# useful bar graph
series.value_counts().plot(kind='bar/barh')

# Pandas Data cleanup
data = data[(data.LATITUDE > 18) & (data.LATITUDE < 20) & ....: (data.LONGITUDE > -75) & (data.LONGITUDE < -70) ....: & data.CATEGORY.notnull()]

# TopN
def top(df, n=5, column): 
  return df.sort_index(by=column)[-n:]