%pip install numpy pandas lightningchart

Downloaded the dataset from - https://github.com/zhouhaoyi/ETDataset

# Import necessary libraries (load pandas library to preprocess dataset)
import pandas as pd

# Line Chart: OT (Oil Temperature) over Time from ETTh1 Dataset
# Developed with AI assistance to showcase the performance of LightningChart Python libraries.

import lightningchart as lc
import pandas as pd

# Load license key
with open("D:/Vindy/HAMK/Internship/MyProjects/lc_license.txt", "r") as f:
    license_key = f.read().strip()

lc.set_license(license_key)

# Load and process data
df = pd.read_csv("ETTh1.csv").head(500)
df['date'] = pd.to_datetime(df['date'])

# Prepare X (time in ms) and Y (OT) data
x = df['date'].astype('int64') // 10**6  # Faster than apply()
y = df['OT']

# Create chart
chart = lc.ChartXY(theme=lc.Themes.Light, title='Line Chart : Transformer Oil Temperature (OT) Over Time (ETTh1)')
line_series = chart.add_line_series()
line_series.add(x.tolist(), y.tolist())

# Configure X and Y axes
x_axis = chart.get_default_x_axis()
x_axis.set_title('Time')
x_axis.set_tick_strategy('DateTime')

y_axis = chart.get_default_y_axis()
y_axis.set_title('Oil Temperature (OT)')

# Optional: Add smoothing or styling
line_series.set_name('OT')
line_series.set_line_thickness(2)

chart.open()

# Point Line Chart: OT vs HUFL over Time from ETTm1 Dataset
# Developed with AI assistance to showcase the performance of LightningChart Python libraries.

import lightningchart as lc
import pandas as pd

# Load license key
with open("D:/Vindy/HAMK/Internship/MyProjects/lc_license.txt", "r") as f:
    license_key = f.read().strip()
lc.set_license(license_key)

# Load and process data
df = pd.read_csv("ETTm1.csv").head(1000)
df['date'] = pd.to_datetime(df['date'])

# Convert datetime to milliseconds
x = df['date'].astype('int64') // 10**6
y_ot = df['OT']
y_hufl = df['HUFL']

# Create chart
chart = lc.ChartXY(theme=lc.Themes.Light, title='Point Line Chart : OT vs HUFL (ETTm1)')

# OT Series
series_ot = chart.add_point_line_series()
series_ot.set_name("OT").set_point_shape('circle').set_point_size(6).set_line_thickness(2)
series_ot.add(x.tolist(), y_ot.tolist())

# HUFL Series
series_hufl = chart.add_point_line_series()
series_hufl.set_name("HUFL").set_point_shape('triangle').set_point_size(6).set_line_thickness(2)
series_hufl.add(x.tolist(), y_hufl.tolist())

# Axis titles
chart.get_default_x_axis().set_title("Time").set_tick_strategy("DateTime")
chart.get_default_y_axis().set_title("Sensor Values")

chart.open()

# Stacked Area Chart: Log-Normalized Transformer Load (ETTh2)
# Developed with AI assistance to showcase the performance of LightningChart Python libraries.

import lightningchart as lc
import pandas as pd
import numpy as np

# Load LightningChart license
with open("D:/Vindy/HAMK/Internship/MyProjects/lc_license.txt", "r") as f:
    lc.set_license(f.read().strip())

# Load ETTh2.csv properly
df = pd.read_csv("ETTh2.csv")
df['date'] = pd.to_datetime(df['date'])  # keep for reference, not used in plot

# Select only the relevant transformer load features
features = ['HUFL', 'HULL', 'MUFL', 'MULL', 'LUFL', 'LULL']
df = df[features]

# Drop missing values if any
df = df.dropna()

# Downsample: average over 10-row windows
window_size = 10
df_downsampled = df.groupby(df.index // window_size).mean()

# Apply logarithmic normalization (log1p to avoid log(0))
log_normalized = np.log1p(np.abs(df_downsampled))

# Create chart
chart = lc.ChartXY()
chart.set_title("Stacked Area Chart: Log-Normalized Transformer Loads (ETTh2)")
chart.get_default_y_axis().set_title("Log-Normalized Load")
chart.get_default_x_axis().set_title("Time Index (Downsampled)")

# Plot each feature using AreaSeries (not stacked visually, just layered)
colors = ['red', 'green', 'blue', 'orange', 'purple', 'cyan']
x_values = list(range(len(log_normalized)))

for i, feature in enumerate(features):
    area = chart.add_area_series()
    area.set_name(feature)
    area.add(x_values, log_normalized[feature].values)
    area.set_fill_color(lc.Color(colors[i]))

# Show chart
chart.open()

# Real-Time Line Chart: Streaming HUFL, MUFL, LUFL from ETTh1 Dataset
# Developed with AI assistance to showcase the performance of LightningChart Python libraries.

import lightningchart as lc
import pandas as pd
import time

# Load LightningChart license
with open("D:/Vindy/HAMK/Internship/MyProjects/lc_license.txt", "r") as f:
    license_key = f.read().strip()
lc.set_license(license_key)

# Load data
df = pd.read_csv("ETTh1.csv").iloc[:300]
df['date'] = pd.to_datetime(df['date'])
features = ['HUFL', 'MUFL', 'LUFL']

# Create chart
chart = lc.ChartXY(title="Real-Time Line Chart : HUFL, MUFL & LUFL (ETTh1)", theme=lc.Themes.Light)
chart.set_animations_enabled(False)

# Make sure axes and grid lines are visible
x_axis = chart.get_default_x_axis()
x_axis.set_title("Time (Simulated Index)")
x_axis.set_tick_strategy("Numeric")
x_axis.set_scroll_strategy('scrolling')
x_axis.set_interval(start=0, end=300, stop_axis_after=False)

y_axis = chart.get_default_y_axis()
y_axis.set_title("Transformer Load Values")
y_axis.set_tick_strategy("Numeric")

# Configure X-axis for streaming
x_axis = chart.get_default_x_axis()
x_axis.set_scroll_strategy('scrolling')
x_axis.set_interval(start=0, end=300, stop_axis_after=False)

# Initialize line series
colors = ['red', 'green', 'blue']
series_list = []
for i, feat in enumerate(features):
    line = chart.add_line_series()
    line.set_name(feat)
    line.set_line_thickness(2)
    line.set_line_color(lc.Color(colors[i]))
    series_list.append(line)

# Show chart in live mode
chart.open(live=True)

# Stream points into the chart
for i in range(len(df)):
    for j, feat in enumerate(features):
        x = i
        y = df.loc[i, feat]
        series_list[j].add(x, y)
    time.sleep(0.02)  # simulate 20 ms real-time interval

chart.close()