def plot_standard_correlation_coefficient():
attr = [
'median_house_value', 'median_income', 'total_rooms',
'housing_median_age'
]
scatter_matrix(data_training[attr], figsize=(12, 8))
plt.show()
def scatter_matrix(frame, alpha=0.5, figsize=None, ax=None, grid=False,
diagonal='hist', marker='.', density_kwds=None,
hist_kwds=None, range_padding=0.05, **kwds):
"""
Draw a matrix of scatter plots.
Parameters
----------
frame : DataFrame
alpha : float, optional
amount of transparency applied
figsize : (float,float), optional
a tuple (width, height) in inches
ax : Matplotlib axis object, optional
grid : bool, optional
setting this to True will show the grid
diagonal : {'hist', 'kde'}
pick between 'kde' and 'hist' for
either Kernel Density Estimation or Histogram
plot in the diagonal
marker : str, optional
Matplotlib marker type, default '.'
hist_kwds : other plotting keyword arguments
To be passed to hist function
density_kwds : other plotting keyword arguments
To be passed to kernel density estimate plot
range_padding : float, optional
relative extension of axis range in x and y
with respect to (x_max - x_min) or (y_max - y_min),
default 0.05
kwds : other plotting keyword arguments
To be passed to scatter function
Returns
-------
numpy.ndarray
A matrix of scatter plots.
Examples
--------
>>> df = pd.DataFrame(np.random.randn(1000, 4), columns=['A','B','C','D'])
>>> scatter_matrix(df, alpha=0.2)
"""
plot_backend = _get_plot_backend()
return plot_backend.scatter_matrix(
frame=frame, alpha=alpha, figsize=figsize, ax=ax, grid=grid,
diagonal=diagonal, marker=marker, density_kwds=density_kwds,
hist_kwds=hist_kwds, range_padding=range_padding, **kwds)
# head
print(dataset.head(20))
# descriptions
print(dataset.describe())
# class distribution
print(dataset.groupby('class').size())
# Data visualisation
# box and whisker plots
dataset.plot(kind='box',
subplots=True,
layout=(2, 2),
sharex=False,
sharey=False)
pyplot.show()
# box and whisker plots
dataset.plot(kind='box',
subplots=True,
layout=(2, 2),
sharex=False,
sharey=False)
pyplot.show()
# histograms
dataset.hist()
pyplot.show()
# scatter plot matrix
scatter_matrix(dataset)
pyplot.show()
# scatter plot matrix
scatter_matrix(dataset)
pyplot.show()
def scatter_matrix(frame,
alpha=0.5,
figsize=None,
ax=None,
grid=False,
diagonal='hist',
marker='.',
density_kwds=None,
hist_kwds=None,
range_padding=0.05,
**kwds):
"""
Draw a matrix of scatter plots.
Parameters
----------
frame : DataFrame
alpha : float, optional
amount of transparency applied
figsize : (float,float), optional
a tuple (width, height) in inches
ax : Matplotlib axis object, optional
grid : bool, optional
setting this to True will show the grid
diagonal : {'hist', 'kde'}
pick between 'kde' and 'hist' for
either Kernel Density Estimation or Histogram
plot in the diagonal
marker : str, optional
Matplotlib marker type, default '.'
hist_kwds : other plotting keyword arguments
To be passed to hist function
density_kwds : other plotting keyword arguments
To be passed to kernel density estimate plot
range_padding : float, optional
relative extension of axis range in x and y
with respect to (x_max - x_min) or (y_max - y_min),
default 0.05
kwds : other plotting keyword arguments
To be passed to scatter function
Returns
-------
numpy.ndarray
A matrix of scatter plots.
Examples
--------
>>> df = pd.DataFrame(np.random.randn(1000, 4), columns=['A','B','C','D'])
>>> scatter_matrix(df, alpha=0.2)
"""
plot_backend = _get_plot_backend()
return plot_backend.scatter_matrix(frame=frame,
alpha=alpha,
figsize=figsize,
ax=ax,
grid=grid,
diagonal=diagonal,
marker=marker,
density_kwds=density_kwds,
hist_kwds=hist_kwds,
range_padding=range_padding,
**kwds)
n_features=dimension)
with open("dataset.txt", "w") as file:
for centroid in points:
for value in range(dimension):
if value == (dimension - 1):
file.write(str(round(centroid[value], 4)))
else:
file.write(str(round(centroid[value], 4)) + ",")
file.write("\n")
data = np.array(points)
# plot
df = pd.DataFrame(data, columns=['x1', 'x2', 'x3'])
scatter_matrix(df, alpha=0.2, figsize=(10, 10))
df = DataFrame(dict(x=points[:, 0], y=points[:, 1], label=y))
colors = {
0: 'red',
1: 'blue',
2: 'green',
3: 'black',
4: 'purple',
5: 'pink',
6: 'orange'
}
fig, ax = pyplot.subplots()
grouped = df.groupby('label')
for key, group in grouped:
group.plot(ax=ax,
df.plot(kind='density', subplots=True, layout=(4, 4), sharex=False, fontsize=8)
plt.suptitle("Density", y=1.00, fontweight='bold')
plt.show()
# box and whisker plots
df.plot(kind='box',
subplots=False,
layout=(4, 4),
sharex=False,
sharey=False,
fontsize=12)
plt.suptitle("Box and Whisker", y=1.00, fontweight='bold')
plt.show()
#endregion
#region Bivariant
# scatter plot matrix
scatter_matrix(df)
plt.suptitle("Scatter Matrix", y=1.00, fontweight='bold')
plt.show()
# correlation matrix
fig = plt.figure()
ax = fig.add_subplot(111)
cax = ax.matshow(df.corr(), vmin=-1, vmax=1, interpolation='none')
fig.colorbar(cax)
ticks = numpy.arange(0, 13, 1)
ax.set_xticks(ticks)
ax.set_yticks(ticks)
ax.set_xticklabels(names)
ax.set_yticklabels(names)
plt.suptitle("Correlation Matrix", y=1.00, fontweight='bold')
plt.show()
#endregion
correlations = train_df.corr()
# Plot figsize
fig, ax = plt.subplots(figsize=(10, 10))
# Generate Color Map
colormap = sns.diverging_palette(220, 10, as_cmap=True)
# Generate Heat Map, allow annotations and place floats in map
sns.heatmap(correlations, cmap=colormap, annot=True, fmt=".2f")
ax.set_xticklabels(
colum_names,
rotation=45,
horizontalalignment='right'
);
ax.set_yticklabels(colum_names);
plt.show()
# Scatterplot Matrix
sm = scatter_matrix(train_df, figsize=(6, 6), diagonal='kde')
#Change label rotation
[s.xaxis.label.set_rotation(40) for s in sm.reshape(-1)]
[s.yaxis.label.set_rotation(0) for s in sm.reshape(-1)]
#May need to offset label when rotating to prevent overlap of figure
[s.get_yaxis().set_label_coords(-0.6,0.5) for s in sm.reshape(-1)]
#Hide all ticks
[s.set_xticks(()) for s in sm.reshape(-1)]
[s.set_yticks(()) for s in sm.reshape(-1)]
plt.show()
# prepare configuration for cross validation test harness
seed = 7
# prepare models
models = []
models.append(('LogisticRegression', LogisticRegression()))
# evaluate the model
def plot_scatter_matrix(dataframe):
scatter_matrix(dataframe, figsize=(15, 11))