def plot(df, idx, weights, mappers=None, cols=4):
"""
Plot bar plots for all columns in the DataFrame.
Parameters
----------
df : pd.DataFrame
A pandas DataFrame object with the data.
idx : iterable
An iterable containing the indices of selected participants.
weights : optional, dict {column: float}
Weighting over dataframe columns
By default, a uniform weighting is used
mappers : optional, dict {column: entrofy.BaseMapper}
Dictionary mapping dataframe columns to BaseMapper objects
Returns
-------
fig_all : list of matplotlib.Figure objects
The list containing all Figure objects with the plots.
"""
if mappers is None:
mappers = construct_mappers(df, weights)
columns = list(mappers.keys())
ncolumns = len(columns)
rows = np.floor(ncolumns/cols)
if (ncolumns % cols) > 0:
rows += 1
fig = plt.figure(figsize=(4*cols, 3*rows))
axes = []
for i,c in enumerate(columns):
ax = fig.add_subplot(rows, cols, i+1)
ax, _ = plot_fractions(df[c], idx, c, mappers[c], ax=ax)
axes.append(ax)
plt.tight_layout()
return axes
def plot(df, idx, weights, mappers=None, cols=4):
"""
Plot bar plots for all columns in the DataFrame.
Parameters
----------
df : pd.DataFrame
A pandas DataFrame object with the data.
idx : iterable
An iterable containing the indices of selected participants.
weights : optional, dict {column: float}
Weighting over dataframe columns
By default, a uniform weighting is used
mappers : optional, dict {column: entrofy.BaseMapper}
Dictionary mapping dataframe columns to BaseMapper objects
Returns
-------
fig_all : list of matplotlib.Figure objects
The list containing all Figure objects with the plots.
"""
if mappers is None:
mappers = construct_mappers(df, weights)
columns = list(mappers.keys())
ncolumns = len(columns)
rows = np.floor(ncolumns/cols)
if (ncolumns % cols) > 0:
rows += 1
fig = plt.figure(figsize=(4*cols, 3*rows))
axes = []
for i,c in enumerate(columns):
ax = fig.add_subplot(rows, cols, i+1)
ax, _ = plot_fractions(df[c], idx, c, mappers[c], ax=ax)
axes.append(ax)
plt.tight_layout()
return axes
def plot_triangle(df, weights, mappers=None, cmap="YlGnBu", bins=30,
prefac=10., cat_type="box", cont_type="hist", fig=None):
"""
Make a triangle plot of all the relevant columns in the DataFrame.
Parameters
----------
df : pd.DataFrame
A pandas DataFrame with the data
weights : optional, dict {column: float}
Weighting over dataframe columns
By default, a uniform weighting is used
mappers : optional, dict {column: entrofy.BaseMapper}
Dictionary mapping dataframe columns to BaseMapper objects
cmap : matplotlib.cm.colormap
A matplotlib colormap to use for shading the bubbles
bins : int
The number of bins for the histogram.
prefac : float
A pre-factor steering the shading of the bubbles
cat_type : {"box" | "strip" | "swarm" | "violin" | "categorical"}
The type of plot for any plot including both categorical and continuous
data.
cont_type : {"kde" | "scatter"}
The type of plot to produce. Either a kernel density estimate ("kde")
or a scatter plor ("scatter").
fig : matplotlib.Figure object
A Figure object to plot in.
Returns
-------
fig : matplotlib.Figure object
The Figure object
axes : list
A list of matplotlib.Axes objects
"""
# if mappers are None, construct them with some default settings
if mappers is None:
mappers = construct_mappers(df, weights)
# the keys
keys = np.sort(list(mappers.keys()))
# the number of panels I'll need
nkeys = len(keys)
# determine the types:
all_types = []
for k in keys:
if isinstance(mappers[k], ObjectMapper):
all_types.append("categorical")
elif isinstance(mappers[k], ContinuousMapper):
all_types.append("continuous")
else:
raise Exception("Data type not recognized!")
# construct the figure
if fig is None:
fig, axes = plt.subplots(nkeys, nkeys, figsize=(4*nkeys, 3*nkeys))
else:
axes = []
k = 1
for i in range(nkeys):
for j in range(nkeys):
axes.append(fig.add_subplot(nkeys, nkeys, k))
k += 1
axes = np.array(axes).reshape((nkeys, nkeys))
for i, kx in enumerate(keys):
for j, ky in enumerate(keys):
xtype = all_types[i]
ytype = all_types[j]
# upper triangle: print white space
if i < j:
axes[i,j].spines['right'].set_visible(False)
axes[i,j].spines['top'].set_visible(False)
axes[i,j].spines['left'].set_visible(False)
axes[i,j].spines['bottom'].set_visible(False)
axes[i,j].set_axis_bgcolor('white')
axes[i,j].set_xlabel("")
axes[i,j].set_ylabel("")
axes[i,j].axis('off')
continue
# diagonal: plot the univariate distribution
elif i == j:
axes[i,j] = plot_distribution(df, kx, xmapper=mappers[kx],
xtype=xtype, ax=axes[i,j],
cmap=cmap, bins=bins)
# upper triangle: plot the bivariate distributions
else:
axes[i,j] = plot_correlation(df, ky, kx, xmapper=mappers[ky],
ymapper=mappers[kx], ax=axes[i,j],
cmap=cmap, xtype=ytype,
ytype=xtype, prefac=prefac,
cat_type=cat_type,
cont_type=cont_type)
if i < nkeys - 1:
axes[i,j].set_xticklabels([])
axes[i,j].set_xlabel("")
else:
[l.set_rotation(45) for l in axes[i,j].get_xticklabels()]
if j > 0:
axes[i,j].set_yticklabels([])
if i != j:
axes[i,j].set_ylabel("")
plt.tight_layout()
return fig, axes
def plot_triangle(df, weights, mappers=None, cmap="YlGnBu", bins=30,
prefac=10., cat_type="box", cont_type="hist", fig=None):
"""
Make a triangle plot of all the relevant columns in the DataFrame.
Parameters
----------
df : pd.DataFrame
A pandas DataFrame with the data
weights : optional, dict {column: float}
Weighting over dataframe columns
By default, a uniform weighting is used
mappers : optional, dict {column: entrofy.BaseMapper}
Dictionary mapping dataframe columns to BaseMapper objects
cmap : matplotlib.cm.colormap
A matplotlib colormap to use for shading the bubbles
bins : int
The number of bins for the histogram.
prefac : float
A pre-factor steering the shading of the bubbles
cat_type : {"box" | "strip" | "swarm" | "violin" | "categorical"}
The type of plot for any plot including both categorical and continuous
data.
cont_type : {"kde" | "scatter"}
The type of plot to produce. Either a kernel density estimate ("kde")
or a scatter plor ("scatter").
fig : matplotlib.Figure object
A Figure object to plot in.
Returns
-------
fig : matplotlib.Figure object
The Figure object
axes : list
A list of matplotlib.Axes objects
"""
# if mappers are None, construct them with some default settings
if mappers is None:
mappers = construct_mappers(df, weights)
# the keys
keys = np.sort(list(mappers.keys()))
# the number of panels I'll need
nkeys = len(keys)
# determine the types:
all_types = []
for k in keys:
if isinstance(mappers[k], ObjectMapper):
all_types.append("categorical")
elif isinstance(mappers[k], ContinuousMapper):
all_types.append("continuous")
else:
raise Exception("Data type not recognized!")
# construct the figure
if fig is None:
fig, axes = plt.subplots(nkeys, nkeys, figsize=(4*nkeys, 3*nkeys))
else:
axes = []
k = 1
for i in range(nkeys):
for j in range(nkeys):
axes.append(fig.add_subplot(nkeys, nkeys, k))
k += 1
axes = np.array(axes).reshape((nkeys, nkeys))
for i, kx in enumerate(keys):
for j, ky in enumerate(keys):
xtype = all_types[i]
ytype = all_types[j]
# upper triangle: print white space
if i < j:
axes[i,j].spines['right'].set_visible(False)
axes[i,j].spines['top'].set_visible(False)
axes[i,j].spines['left'].set_visible(False)
axes[i,j].spines['bottom'].set_visible(False)
axes[i,j].set_axis_bgcolor('white')
axes[i,j].set_xlabel("")
axes[i,j].set_ylabel("")
axes[i,j].axis('off')
continue
# diagonal: plot the univariate distribution
elif i == j:
axes[i,j] = plot_distribution(df, kx, xmapper=mappers[kx],
xtype=xtype, ax=axes[i,j],
cmap=cmap, bins=bins)
# upper triangle: plot the bivariate distributions
else:
axes[i,j] = plot_correlation(df, ky, kx, xmapper=mappers[ky],
ymapper=mappers[kx], ax=axes[i,j],
cmap=cmap, xtype=ytype,
ytype=xtype, prefac=prefac,
cat_type=cat_type,
cont_type=cont_type)
if i < nkeys - 1:
axes[i,j].set_xticklabels([])
axes[i,j].set_xlabel("")
else:
[l.set_rotation(45) for l in axes[i,j].get_xticklabels()]
if j > 0:
axes[i,j].set_yticklabels([])
if i != j:
axes[i,j].set_ylabel("")
plt.tight_layout()
return fig, axes
