def _plotly_viz_plot_time_series(df,
col,
result=None,
decompose=False,
title="Time Series"):
"""Create timeseries visualization.
Args:
df: The dataframe
col (str or [str]): Column of interest. Column datatype must be numerical.
result: The statsmodels.tsa.seasonal.DecomposeResult object. Defaults to None.
decompose: Set as True to decompose the timeseries with moving average. result must not be None. Defaults to False.
title: Title of the plot. Defaults to "Time Series".
Returns:
The visualization
"""
if isinstance(col, list):
data = [go.Scatter(x=df.index, y=df[c], name=c) for c in col]
ylabel = "Variable" if len(col) > 1 else col[0]
fig = go.Figure(data=data,
layout=figure_layout(title=title, ylabel=ylabel))
elif isinstance(col, str) and not decompose:
fig = go.Figure(
data=go.Scatter(x=df.index, y=df[col], name=col),
layout=figure_layout(title=title, ylabel=col),
)
elif decompose:
fig = _plotly_viz_decomposition(result, dates=df.index)
if _in_notebook():
init_notebook_mode(connected=True)
return iplot(fig, config={"displayModeBar": False})
else:
return fig
def _pyldavis_viz_visualize_topic_summary(
model: "gensim.models.ldamodel.LdaModel", # type: ignore
corpus: List[List[Tuple[int, int]]],
dictionary: "gensim.corpora.dictionary.Dictionary", # type: ignore
):
"""Displays interactive pyLDAvis visual to understand topic model and documents.
Args:
model: LDA topic model
corpus: Bag of Words (BoW) representation of documents (token_id, token_count)
dictionary: Gensim Dictionary encapsulates the mapping between normalized words
and their integer ids.
Raises:
EnvironmentError: Must be in a Notebook.
Returns:
A visual to understand topic model and/or documents relating to model
"""
if not _in_notebook():
raise EnvironmentError("Not in Jupyter Notebook")
_compat["pyLDAvis"].enable_notebook() # type: ignore
with warnings.catch_warnings():
warnings.filterwarnings(
"ignore",
category=FutureWarning,
module="pyLDAvis",
message="Sorting because non-concatenation axis is not aligned.",
)
vis = _compat["pyLDAvis"].gensim.prepare(model, corpus,
dictionary) # type: ignore
return vis
def _plotly_viz_correlation_matrix(association_matrix):
"""Plot the heatmap for the association matrix.
Args:
association_matrix (DataFrame): The association matrix
Returns:
The plotly figure
"""
# Plot lower left triangle
x_ind, y_ind = np.triu_indices(association_matrix.shape[0])
corr = association_matrix.to_numpy()
for x, y in zip(x_ind, y_ind):
corr[x, y] = None
# Set up the color scale
cscale = mpl_to_plotly_cmap(get_p_RdBl_cmap())
# Generate a custom diverging colormap
fig = go.Figure(
data=[
go.Heatmap(
z=np.flip(corr, axis=0),
x=association_matrix.columns.values,
y=association_matrix.columns.values[::-1],
connectgaps=False,
xgap=2,
ygap=2,
zmid=0,
colorscale=cscale,
colorbar={"title": "Strength"},
)
],
layout=go.Layout(
autosize=False,
width=get_option("display.plotly.fig_width"),
height=get_option("display.plotly.fig_height"),
title={
"text": "Correlation Matrix",
"font": {
"size": get_option("display.plotly.title_size")
},
},
xaxis=go.layout.XAxis(automargin=True,
tickangle=270,
ticks="",
showgrid=False),
yaxis=go.layout.YAxis(automargin=True, ticks="", showgrid=False),
plot_bgcolor="rgb(0,0,0,0)",
paper_bgcolor="rgb(0,0,0,0)",
),
)
if _in_notebook():
po.init_notebook_mode(connected=True)
return po.iplot(fig, config={"displayModeBar": False})
else:
return fig
def _plotly_viz_data_heatmap(data,
colnames: List[str],
missing: bool = False,
**kwargs):
"""Plots the data heatmap.
Args:
data: The dataframe
colnames (List[str]): The column names, used for tick labels
missing (bool): If True, plots missing values instead
**kwargs: Keyword arguments.
Returns:
The data heatmap as a Plotly figure.
"""
data_fig = go.Heatmap(
z=np.flip(data.values, axis=0),
x=list(range(data.shape[0])),
y=list(colnames[::-1]),
ygap=1,
zmin=-3 if not missing else 0,
zmax=3 if not missing else 1,
colorscale="viridis" if not missing else "greys",
colorbar={"title": "z-score (bounded)" if not missing else "Missing"},
)
figure = go.Figure(
data=[data_fig],
layout=go.Layout(
autosize=False,
title={
"text": "Data Heatmap",
"font": {
"size": get_option("display.plotly.title_size")
},
},
width=get_option("display.plotly.fig_width"),
height=get_option("display.plotly.fig_height"),
xaxis=go.layout.XAxis(ticks="", title="Record #", showgrid=False),
yaxis=go.layout.YAxis(ticks="",
title="Variable",
automargin=True,
showgrid=False),
plot_bgcolor="rgb(0,0,0,0)",
paper_bgcolor="rgb(0,0,0,0)",
),
)
if _in_notebook():
init_notebook_mode(connected=True)
return iplot(figure, config={"displayModeBar": False})
else:
return figure
def _plotly_viz_cluster(
data,
method: str,
xlabel: Optional[str] = None,
ylabel: Optional[str] = None,
**kwargs,
):
"""Visualize clusters using Plotly.
Args:
data (DataFrame): The data
method (str): The clustering method, to be used as the plot title
xlabel (str, optional): The x-axis label. Defaults to "Reduced Dimension 1".
ylabel (str, optional): The y-axis label. Defaults to "Reduced Dimension 2".
**kwargs: Keyword arguments.
Returns:
Plotly plot
"""
xlabel = xlabel or "Reduced Dimension 1"
ylabel = ylabel or "Reduced Dimension 2"
labels = data["clusters"].unique()
trace_list = []
for i in labels:
if int(i) < 0:
trace = go.Scatter(
x=data.loc[data["clusters"] == i, "x"],
y=data.loc[data["clusters"] == i, "y"],
name="Noise",
mode="markers",
marker=dict(size=10, color="grey", line=None, opacity=0.7),
)
trace_list.append(trace)
else:
trace = go.Scatter(
x=data.loc[data["clusters"] == i, "x"],
y=data.loc[data["clusters"] == i, "y"],
name=f"Cluster #{i}",
mode="markers",
marker=dict(size=10,
colorscale="earth",
line=None,
opacity=0.7),
)
trace_list.append(trace)
layout = dict(
yaxis=dict(zeroline=False, title=data.columns[0]),
xaxis=dict(zeroline=False, title=data.columns[1]),
yaxis_title=ylabel,
xaxis_title=xlabel,
autosize=False,
width=int(get_option("display.plotly.fig_width")),
height=int(get_option("display.plotly.fig_height")),
title={
"text": "{} Cluster".format(method),
"font": {
"size": get_option("display.plotly.title_size")
},
},
)
fig = go.Figure(dict(data=trace_list, layout=layout))
if _in_notebook():
po.init_notebook_mode(connected=True)
return po.iplot(fig)
else:
return fig