def plotDensity(data, name, pdf):
"""
This function takes a pandas dataframe and plots a
density plot and a boxplot.
"""
# Stablishing figure layout (x,y,colspan,rowspan)
axisLayout = [(0, 0, 1, 3), (3, 0, 1, 1)]
# Creating a figure template
figure = figureHandler(proj='2d',
numAx=2,
numRow=4,
numCol=1,
figsize=(8, 13),
arrangement=axisLayout)
# Adding figure Title
figure.formatAxis(figTitle="Distribution by Features {0}".format(name),
xlim="ignore",
ylim="ignore",
axnum=0,
showX=False)
#Creting list of len(wide.T) maximu 50 with the colors for each index
colors = [palette.ugColors[name]] * len(data.index)
# Plotting boxPlot
box.boxDF(ax=figure.ax[0], colors=colors, dat=data.T, vert=False, rot=0)
# Plotting density plot
density.plotDensityDF(data=data.T.unstack(),
ax=figure.ax[1],
colors=colors[0])
# Adding figure to pdf object
figure.addToPdf(pdf)
def plotBoxplotDistribution(pdf, wide, palette):
# Instanciating figureHandler object
figure = figureHandler(proj="2d",
figsize=(max(len(wide.columns) / 4, 12), 7))
# Formating axis
figure.formatAxis(figTitle="Distribution by Samples Boxplot",
ylim="ignore",
grid=False,
xlim="ignore")
# Plotting boxplot
box.boxDF(ax=figure.ax[0], colors=palette.design["colors"], dat=wide)
# Shrinking figure
figure.shrink()
#Adding to PDF
figure.addToPdf(pdf, dpi=600)
def plotDistances(df_distance, palette, plotType, disType, cutoff, p, pdf):
#Geting number of samples in dataframe (ns stands for number of samples)
ns = len(df_distance.index)
#Calculates the widht for the figure base on the number of samples
figWidth = max(ns / 2, 16)
# Keeping the order on the colors
df_distance["colors"] = palette.design["colors"]
# Create figure object with a single axis
figure = figureHandler(proj='2d', figsize=(figWidth, 8))
# Getting type of distance file
if "distance_to_mean" in df_distance.columns:
dataType = "to the mean"
else:
dataType = "pairwise"
# Getting ty of distance header
if disType == "Mahalanobis":
distType1 = "Penalized"
distType2 = disType
else:
distType1 = "Standardized"
distType2 = disType
# Adds Figure title, x axis limits and set the xticks
figure.formatAxis(figTitle="{0} for {1} {2} Distance for {3} {4}".format(
plotType, distType1, distType2, df_distance.name, dataType),
yTitle="{0} {1} Distance".format(distType1, distType2),
xTitle="Index",
ylim="ignore",
xlim=(-0.5, -0.5 + ns),
xticks=df_distance.index)
# If distance to mean
if dataType == "to the mean":
# Plot scatterplot quickplot
scatter.scatter2D(ax=figure.ax[0],
colorList=df_distance["colors"],
x=range(len(df_distance.index)),
y=df_distance["distance_to_mean"])
# if pairwise
else:
if plotType == "Scatterplot":
# Plot scatterplot
for index in df_distance.index:
scatter.scatter2D(ax=figure.ax[0],
colorList=df_distance["colors"][index],
x=range(len(df_distance.index)),
y=df_distance[index])
elif plotType == "Box-plots":
# Plot Box plot
box.boxDF(ax=figure.ax[0],
colors=df_distance["colors"],
dat=df_distance)
# Shrink figure
figure.shrink()
# Plot legend
figure.makeLegend(figure.ax[0], palette.ugColors, palette.combName)
#Add a cutoof line
cutoff.apply(lambda x: plotCutoffs(x, ax=figure.ax[0], p=p), axis=0)
# Add figure to PDF and close the figure afterwards
figure.addToPdf(pdf)
# Drop "color" column to no mess the results
df_distance.drop("colors", axis=1, inplace=True)
def makePlots(SEDData, design, pdf, groupName, cutoff, p, plotType, ugColors,
levels):
"""
Manage all the plots for this script
:Arguments:
:type SEDData: pandas.dataFrame
:param SEDData: Contains SED data either to Mean or pairwise
:type design: pandas.dataFrame
:param design: Design file after getColor
:type pdf: PDF object
:param pdf: PDF for output plots
:type groupName: string
:param groupName: Name of the group (figure title).
:type cutoff: pandas.dataFrame
:param cutoff: Cutoff values, beta, chi-sqr and normal.
:type p: float
:param p: Percentil for cutoff.
:type plotType: string
:param plotType: Type of plot, the possible types are scatterplot to mean
scatterplot pairwise and boxplot pairwise.
"""
#Geting number of features in dataframe
nFeatures = len(SEDData.index)
#Calculates the widht for the figure base on the number of features
figWidth = max(nFeatures / 2, 16)
# Create figure object with a single axis and initiate the figss
figure = figureHandler(proj='2d', figsize=(figWidth, 8))
# Keeping the order on the colors
SEDData["colors"] = design["colors"]
# Choose type of plot
# Plot scatterplot to mean
if (plotType == "scatterToMean"):
#Adds Figure title, x axis limits and set the xticks
figure.formatAxis(
figTitle=
"Standardized Euclidean Distance from samples {} to the mean".
format(groupName),
xlim=(-0.5, -0.5 + nFeatures),
ylim="ignore",
xticks=SEDData.index.values,
xTitle="Index",
yTitle="Standardized Euclidean Distance")
#Plot scatterplot quickplot
scatter.scatter2D(ax=figure.ax[0],
colorList=SEDData["colors"],
x=range(len(SEDData.index)),
y=SEDData["SED_to_Mean"])
#Plot scatterplot pairwise
elif (plotType == "scatterPairwise"):
# Adds Figure title, x axis limits and set the xticks
figure.formatAxis(
figTitle="Pairwise standardized Euclidean Distance from samples {}"
.format(groupName),
xlim=(-0.5, -0.5 + nFeatures),
ylim="ignore",
xticks=SEDData.index.values,
xTitle="Index",
yTitle="Standardized Euclidean Distance")
# Plot scatterplot
for index in SEDData.index.values:
scatter.scatter2D(ax=figure.ax[0],
colorList=design["colors"][index],
x=range(len(SEDData.index)),
y=SEDData[index])
#Plot boxplot pairwise
elif (plotType == "boxplotPairwise"):
# Add Figure title, x axis limits and set the xticks
figure.formatAxis(
figTitle=
"Box-plots for pairwise standardized Euclidean Distance from samples {}"
.format(groupName),
xlim=(-0.5, -0.5 + nFeatures),
ylim="ignore",
xticks=SEDData.index.values,
xTitle="Index",
yTitle="Standardized Euclidean Distance")
# Plot Box plot
box.boxDF(ax=figure.ax[0],
colors=SEDData["colors"].values,
dat=SEDData)
#Add a cutoof line
cutoff.apply(lambda x: plotCutoffs(x, ax=figure.ax[0], p=p), axis=0)
figure.shrink()
# Plot legend
#if group:
figure.makeLegend(figure.ax[0], ugColors, levels)
# Add figure to PDF and close the figure afterwards
figure.addToPdf(pdf)