RescueT Produc Plot.ipynb

# Import necessary libraries for the plot
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib.colors import LinearSegmentedColormap
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
from scipy.interpolate import make_interp_spline
from matplotlib.colors import LinearSegmentedColormap

# Given productivity scores data
scores = {
    2016: {9: 62, 10: 63, 11: 68, 12: 73},
    2017: {1: 71, 2: 70, 3: 79, 4: 78, 5: 70, 6: 77, 7: 74, 8: 64, 9: 65, 10: 62, 11: 54, 12: 49},
    2018: {1: 44, 2: 65, 3: 57, 4: 49, 5: 54, 6: 45, 7: 33, 8: 36, 9: 48, 10: 58, 11: 76, 12: 81},
    2019: {1: 70, 2: 68, 3: 71, 4: 84, 5: 79, 6: 78, 7: 68, 8: 62, 9: 73, 10: 83, 11: 79, 12: 79},
    2020: {1: 69, 2: 70, 3: 58, 4: 46, 5: 64, 6: 60, 7: 75, 8: 49, 9: 71, 10: 75, 11: 68, 12: 61},
    2021: {1: 67, 2: 66, 3: 45, 4: 50, 5: 50, 6: 54, 7: 61, 8: 48, 9: 54, 10: 59, 11: 56, 12: 54},
    2022: {1: 49, 2: 46, 3: 53, 4: 56, 5: 45, 6: 42, 7: 49, 8: 39, 9: 51, 10: 61, 11: 54, 12: 52},
    2023: {1: 82, 2: 85, 3: 77, 4: 78, 5: 71, 6: 60, 7: 23, 8: 43, 9: 66, 10: 91, 11: 90, 12: 89},
}

# Plotting
plt.figure(figsize=(40, 10))

# Add vertical lines to separate years
plt.vlines(
    x=[4, 16, 28, 40, 52, 64, 76],
    ymin=0,
    ymax=100,
    colors="#eba434",
    linestyles="dashed",
    label="Year Separators",
)

all_scores = [scores[year][month] for year in scores for month in scores[year]]
dates = [f"{month}/{year}" for year in scores for month in scores[year]]
xpoints = np.array(list(range(len(all_scores))))

# Create a Pandas DataFrame
df = pd.DataFrame({"Date": dates, "Score": all_scores})

# Calculate the moving average with a window size of 3
df["Moving_Avg"] = df["Score"].rolling(window=3).mean()

# Calculate the standard deviation with the same window size
df["Std_Dev"] = df["Score"].rolling(window=3).std()

# Calculate the upper and lower bounds for the confidence interval
df["Upper_Bound"] = df["Moving_Avg"] + (2 * df["Std_Dev"])
df["Lower_Bound"] = df["Moving_Avg"] - (2 * df["Std_Dev"])

# Create more points for a smoother curve
xnew = np.linspace(xpoints.min(), xpoints.max(), 300)

# Interpolation for original scores
spl = make_interp_spline(xpoints, df["Score"], k=3)
y_smooth = spl(xnew)

# Interpolation for confidence intervals
spl_upper = make_interp_spline(
    xpoints[~np.isnan(df["Upper_Bound"])], df["Upper_Bound"].dropna(), k=3
)
y_upper_smooth = spl_upper(xnew)

spl_lower = make_interp_spline(
    xpoints[~np.isnan(df["Lower_Bound"])], df["Lower_Bound"].dropna(), k=3
)
y_lower_smooth = spl_lower(xnew)

# Define the colormap to transition from red to blue
colors = [(1, 0, 0), (0, 0, 1)]  # Red to blue
n_bins = 100
cmap_name = "red_to_blue"
colormap = LinearSegmentedColormap.from_list(cmap_name, colors, N=n_bins)

# Plot the original scores with gradient color
norm = plt.Normalize(y_smooth.min(), y_smooth.max())
for i in range(len(y_smooth) - 1):
    plt.plot(
        xnew[i : i + 2], y_smooth[i : i + 2], c=colormap(norm(y_smooth[i])), linewidth=2
    )

# Add a colorbar for original scores
sm = plt.cm.ScalarMappable(cmap=colormap, norm=norm)
sm.set_array([])
plt.colorbar(
    sm,
    ticks=np.linspace(0, 100, 11),
    boundaries=np.arange(-0.05, 100.1, 0.1),
    label="Original Scores",
)


# Plot the confidence intervals with interpolation for smoothness
plt.fill_between(
    xnew,
    y_upper_smooth,
    y_lower_smooth,
    color="grey",
    alpha=0.5,
    label="Confidence Interval (Smoothed)",
)


plt.xticks(ticks=xpoints, labels=dates, rotation=90)
plt.yticks(range(0, 101, 10))
plt.ylim(0, 100)
plt.title("Productivity Scores Over the Years (Smoothed, With Gradient Color)")
plt.xlabel("Months")
plt.ylabel("Productivity Score")
plt.grid(axis="y")
plt.legend()

plt.show()