07b. Dengue features (parallel)

This Python script uses the pandas and Plotly libraries to create an interactive parallel coordinates plot. This type of plot is excellent for visualizing and exploring relationships in datasets with many variables (high-dimensional data). Each vertical line represents a different variable (a column from the dataset), and each colored line that snakes across the plot represents a single data point (a row from the dataset).

Out:

C:\Users\kelda\Desktop\repositories\github\python-spare-code\main\examples\plotly\plot_main07_parallel_v2.py:63: DtypeWarning:

Columns (3,5,7,9,12,14,15,16,17,18,19,20,21,23,24,25,26,27,28,29,30,33,34,37,40,41,42,43,44,48,49,50,51,52,53,54,55,56,57,61,62,64,66,67,68,69,70,73,74,75,77,79,80,81,82,83,84,85,87,88,89,90,95,96,97,99,101,102,103,104,107,108,110,113,115,117,119,120,121,122,125,126,127,129,130,132,133,134,135,136,137,143,152,153,155,156,157,159,161,162,163,164,165,166,167,168,174,175,176,177,178,182,184,193,197,198,199,200,202,203,207,208,209,213,214,215,218,219,220,221,224,225,226,227,229,232,233,234,235,236,237,238,240,241,242,244,247,250,253,254,255,259,261,262,263,264,265,266,267,268,270,271,272,273,274,275,276,277,278,279,280,281,283,284,285,286,287,288,289,290,291,292,293,294,295,296,297,301,302,303,304,305,307,308,309,310,311,312,313,314,315,317,318,319,320,324,325,326,327,328,330,333,334,335,336,337,338,339,340,343,344,345,346,347,348,349,350,351,352,353,354,355,356,357,358,359,360,361,362,363,364,365,366,367,368,369,370,371,372,373,374,375,376,377,378,379,381,382,384,385,386,391,392,393,395,398,403,404,407,408,409,410,411,412,413,414,415,416,417,418,419,424) have mixed types. Specify dtype option on import or set low_memory=False.

import plotly.graph_objects as go

import numpy as np
import pandas as pd
from pandas.api.types import is_string_dtype
from pandas.api.types import is_numeric_dtype

from plotly.io import show

try:
    __file__
    TERMINAL = True
except:
    TERMINAL = False


def load_gridsearch_sklearn_iris():
    """This method..."""
    # Define datapath
    FILEPATH = './data/sklearn-gridsearch/ls2d-iris.csv'
    # Load data
    df = pd.read_csv(FILEPATH)
    # Columns
    columns = [
        ('mean_train_spearman', 'Spearman'),
        ('mean_train_pearson', 'Pearson'),
        ('param_sae__max_epochs', 'Max Epochs'),
        ('param_sae__lr', 'Learning Rate'),
        ('mean_train_procrustes', 'Procrustes'),
        ('mean_train_calinski_target', 'Calinski'),
        ('mean_train_davies_b_target', 'Davies'),
        #('param_sae__module__layers', 'Layers')
    ]
    # Line
    line = dict(color=df.mean_train_calinski_target,
       colorscale='Electric',
       showscale=True,
       cmin=df.mean_train_calinski_target.min(),
       cmax=df.mean_train_calinski_target.max())
    # Return
    return df, line, columns



def load_raw_dengue():
    """This method..."""
    # Define datapath
    FILEPATH = '../../datasets/dengue-htd-dataset/combined.csv'
    # Load data
    df = pd.read_csv(FILEPATH)
    # Columns
    columns = [
        ('age', 'Age'),
        ('body_temperature', 'Body Temperature'),
        ('weight', 'Weight'),
        ('plt', 'Platelets'),
        ('haematocrit_percent', 'Haematocrit')
    ]
    # Line
    line = dict(color=df.haematocrit_percent,
        colorscale='Electric',
        showscale=True,
        cmin=df.haematocrit_percent.min(),
        cmax=df.haematocrit_percent.max())
    # Return
    return df, line, columns

def create_dimension(s):
    """This method creates the dimesions.

    Dimension: numeric
    dict(range = [32000,227900],
         constraintrange = [100000,150000],
         label = "Block Height",
         values = df['blockHeight'])

    Dimension: enumerated
    dict(tickvals = [0,0.5,1,2,3],
         ticktext = ['A','AB','B','Y','Z'],
         label = 'Cyclinder Material',
         values = df['cycMaterial'],
         visible = True)
    """
    if is_numeric_dtype(s):
        return dict(
            range=[s.min(), s.max()],
            constraintrange=[s.min(), s.max()],
            label=s.name, values=s)
    if is_string_dtype(s):
        s = s.apply(str)
        return dict(tickvals=np.arange(s.nunique()),
            ticktext=sorted(s.unique()),
            label=s.name, values=s)


# Load data
df, line, columns = load_raw_dengue()
#df, columns = load_gridsearch_sklearn_iris()

# Show
fig = go.Figure(data=
    go.Parcoords(line=line,
        dimensions=[create_dimension(df[name])
            for name, label in columns]
    ))


# Show
show(fig)