Upload 102 files

ChartMimic/dataset/ori_500/area_1.py

@@ -0,0 +1,116 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Data for plotting
+x = [1, 2, 3, 4, 5]
+y1 = [18, 24, 27, 29, 29.5]
+y2 = [12, 17, 21, 23, 24]
+y3 = [6, 10, 12, 14, 15]
+y4 = [5, 6, 7, 8, 8.5]
+
+# Labels for legend
+label_activity_net_mIoU = "ActivityNet mIoU"
+label_breakfast_mof = "Breakfast MoF"
+label_activity_net_cider = "ActivityNet CIDEr"
+label_qvhighlights_map = "QVHighlights mAP"
+
+# Plot limits
+xlim_values = (1, 5)
+ylim_values = (0, 35)
+
+# Axis labels
+xlabel_values = ["10K", "50K", "1M", "5M", "10M"]
+ylabel_values = [0, 10, 20, 30, 34]
+
+# Axis ticks
+xticks_values = x
+yticks_values = [0, 10, 20, 30, 34]
+
+# Horizontal line value
+axhline_value = 30
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+# Plotting the data
+plt.figure(figsize=(9, 8))  # Adjusting figure size to match original image dimensions
+plt.plot(
+    x,
+    y1,
+    "o-",
+    clip_on=False,
+    zorder=10,
+    markerfacecolor="#eec7bb",
+    markeredgecolor="#d77659",
+    markersize=12,
+    color="#d77659",
+    label=label_activity_net_mIoU,
+)
+plt.plot(
+    x,
+    y2,
+    "o-",
+    clip_on=False,
+    zorder=10,
+    markerfacecolor="#f5dbc3",
+    markeredgecolor="#e8a66c",
+    markersize=12,
+    color="#e8a66c",
+    label=label_breakfast_mof,
+)
+plt.plot(
+    x,
+    y3,
+    "o-",
+    clip_on=False,
+    zorder=10,
+    markerfacecolor="#b4d7d1",
+    markeredgecolor="#509b8d",
+    markersize=12,
+    color="#509b8d",
+    label=label_activity_net_cider,
+)
+plt.plot(
+    x,
+    y4,
+    "o-",
+    clip_on=False,
+    zorder=10,
+    markerfacecolor="#abb5ba",
+    markeredgecolor="#2e4552",
+    markersize=12,
+    color="#2e4552",
+    label=label_qvhighlights_map,
+)
+
+# Filling the area under the curves
+plt.fill_between(x, y1, y2, color="#eec7bb", alpha=1)
+plt.fill_between(x, y2, y3, color="#f5dbc3", alpha=1)
+plt.fill_between(x, y3, y4, color="#b4d7d1", alpha=1)
+plt.fill_between(x, y4, color="#abb5ba", alpha=1)
+
+# Adding a horizontal dashed line at y=axhline_value
+plt.axhline(axhline_value, color="black", linestyle="dotted")
+
+# Setting the x-axis、y-axis limits
+plt.xlim(*xlim_values)
+plt.ylim(*ylim_values)
+
+# Setting the x-axis tick labels
+plt.xticks(xticks_values, xlabel_values)
+plt.yticks(yticks_values, ylabel_values)
+
+# Adding a legend
+plt.legend(loc="lower center", ncol=4, bbox_to_anchor=(0.5, -0.1), frameon=False)
+plt.gca().tick_params(axis="both", which="both", length=0)
+
+# ===================
+# Part 4: Saving Output
+# ===================
+plt.tight_layout()
+plt.savefig("area_1.pdf", bbox_inches="tight")

ChartMimic/dataset/ori_500/area_4.py

@@ -0,0 +1,102 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+import numpy as np
+
+np.random.seed(0)
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Data
+n_aug = ["0", "0.125", "0.25", "0.5", "1", "2", "4", "8"]
+content = np.array([1, 3, 6, 4, 2, 1, 0.5, 0.2])
+organization = np.array([0.5, 1, 1.5, 2, 1.5, 1, 0.5, 0.25])
+language = np.array([0, 0.5, 1, 2, 4, 3, 2, 1])
+
+# Calculate cumulative values for stacked area chart
+cumulative_content = content
+cumulative_organization = cumulative_content + organization
+cumulative_language = cumulative_organization + language
+
+# Positions for the bars on the x-axis
+ind = np.arange(len(n_aug))
+
+# Variables for plot configuration
+content_label = "Content"
+organization_label = "Organization"
+language_label = "Language"
+xlim_values = (0, 7)
+ylim_values = (0, 10)
+xlabel_text = "n"
+ylabel_text = "Performance Gain (%)"
+title_text = "Cumulative Performance Gain by Augmentation Level"
+yticks_values = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
+legend_location = "upper center"
+legend_fontsize = 12
+legend_frameon = False
+legend_shadow = True
+legend_facecolor = "#ffffff"
+legend_ncol = 3
+legend_bbox_to_anchor = (0.5, 1.2)
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+# Plot
+fig, ax = plt.subplots(figsize=(8, 4))  # Adjusted for better aspect ratio
+ax.fill_between(
+    n_aug, 0, cumulative_content, label=content_label, color="#0173b2", alpha=0.7
+)
+ax.fill_between(
+    n_aug,
+    cumulative_content,
+    cumulative_organization,
+    label=organization_label,
+    color="#de8f05",
+    alpha=0.7,
+)
+ax.fill_between(
+    n_aug,
+    cumulative_organization,
+    cumulative_language,
+    label=language_label,
+    color="#20a983",
+    alpha=0.7,
+)
+
+# Enhancing the plot with additional visuals
+ax.spines["top"].set_visible(False)
+ax.spines["right"].set_visible(False)
+ax.spines["left"].set_visible(False)
+ax.spines["bottom"].set_visible(False)
+ax.set_yticks(yticks_values)
+# Setting the x-axis and y-axis limits dynamically
+ax.set_ylim(*ylim_values)  # Ensure all data fits well
+ax.set_xlim(*xlim_values)
+# Labels, Title and Grid
+ax.set_xlabel(xlabel_text, fontsize=14)
+ax.set_ylabel(ylabel_text, fontsize=14)
+ax.set_title(title_text, fontsize=16, y=1.2)
+ax.tick_params(axis="both", which="both", color="gray")
+# Custom legend
+ax.legend(
+    loc=legend_location,
+    fontsize=legend_fontsize,
+    frameon=legend_frameon,
+    shadow=legend_shadow,
+    facecolor=legend_facecolor,
+    ncol=legend_ncol,
+    bbox_to_anchor=legend_bbox_to_anchor,
+)
+
+# Grid
+ax.grid(True, linestyle="--", alpha=0.5, which="both")
+
+# ===================
+# Part 4: Saving Output
+# ===================
+# Adjusting layout to reduce white space
+plt.tight_layout()
+plt.savefig("area_4.pdf", bbox_inches="tight")

ChartMimic/dataset/ori_500/area_5.py

@@ -0,0 +1,65 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+import numpy as np
+
+np.random.seed(0)
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+year = [1950, 1960, 1970, 1980, 1990, 2000, 2010, 2018]
+population_by_continent = {
+    "africa": [228, 284, 365, 477, 631, 814, 1044, 1275],
+    "americas": [943, 606, 540, 727, 840, 425, 519, 619],
+    "asia": [1394, 1686, 2120, 1625, 1202, 1714, 2169, 2560],
+    "europe": [220, 253, 276, 295, 310, 303, 294, 293],
+    "oceania": [200, 300, 340, 360, 280, 260, 320, 280],
+}
+
+# Extracted variables
+legend_labels = list(population_by_continent.keys())
+xlim_values = (1950, 2018)
+ylim_values = (0, 6000)
+xlabel_value = "Year"
+ylabel_value = "Number of people (millions)"
+title_value = "World population"
+legend_loc = "upper center"
+legend_reverse = False
+legend_frameon = False
+legend_ncol = 5
+legend_bbox_to_anchor = (0.5, 1.08)
+title_y_position = 1.08
+colors = ["#b2e7aa", "#fae18f", "#d75949", "#f0906d", "#a1a8d6"]
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+fig, ax = plt.subplots(figsize=(8, 6))
+ax.stackplot(
+    year,
+    population_by_continent.values(),
+    labels=legend_labels,
+    alpha=0.8,
+    colors=colors,
+)
+ax.legend(
+    loc=legend_loc,
+    reverse=legend_reverse,
+    frameon=legend_frameon,
+    ncol=legend_ncol,
+    bbox_to_anchor=legend_bbox_to_anchor,
+)
+ax.set_xlim(*xlim_values)
+ax.set_ylim(*ylim_values)
+ax.set_title(title_value, y=title_y_position)
+ax.set_xlabel(xlabel_value)
+ax.set_ylabel(ylabel_value)
+ax.tick_params(axis="both", which="both", length=0)
+
+# ===================
+# Part 4: Saving Output
+# ===================
+plt.tight_layout()
+plt.savefig("area_5.pdf", bbox_inches="tight")

ChartMimic/dataset/ori_500/bar_51.py

@@ -0,0 +1,50 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Data
+professions = [
+    "Farmer",
+    "Scooter mechanic",
+    "Household management",
+    "Construction/Renovation",
+    "Gardening",
+    "Making Bricks",
+    "Carpenter",
+    "Baker",
+    "Crafting/knitting",
+    "Cleaning / laundry",
+]
+number_of_videos = [2008, 2060, 2158, 2343, 2548, 2915, 3216, 3543, 4190, 5375]
+
+# Axes Limits and Labels
+xlabel_value = "Number of Videos"
+title = "Number of Videos by Profession"
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+# Create horizontal bar chart
+plt.figure(figsize=(12, 8))  # Adjust figure size to match original image's dimensions
+plt.barh(professions, number_of_videos, color="#685bc6")  # Change bar color to purple
+plt.xlabel(xlabel_value)
+plt.title(title)
+
+# Add data labels
+for index, value in enumerate(number_of_videos):
+    plt.text(
+        value + 50, index, str(value), va="center", fontsize=10
+    )  # Adjust text position and font size
+
+plt.yticks(rotation=45)
+
+# ===================
+# Part 4: Saving Output
+# ===================
+# Displaying the plot with tight layout to minimize white space
+plt.tight_layout()
+plt.savefig("bar_51.pdf", bbox_inches="tight")

ChartMimic/dataset/ori_500/bar_6.py

@@ -0,0 +1,74 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Emotion labels
+emotions = [
+    "Amusement",
+    "Unbothered",
+    "Sadness",
+    "Pride",
+    "Nervousness",
+    "Annoyance",
+    "Gratitude",
+    "Relief",
+    "Joy",
+    "Disapproval",
+    "Excitement",
+    "Delight",
+    "Oblivious",
+    "Embarrassment",
+    "Disappointment",
+]
+
+# Approximate frequency values based on the image
+frequencies = [
+    2.1,
+    2.7,
+    3.0,
+    3.5,
+    3.5,
+    3.8,
+    4.0,
+    4.0,
+    6.0,
+    6.0,
+    6.0,
+    6.6,
+    6.7,
+    7.0,
+    7.6,
+]
+
+xlabel = "Frequency (%)"
+ylabel = "Emotion"
+xticks = list(range(0, 9))
+xlim = [0, 8.5]
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+# Create horizontal bar chart
+plt.figure(figsize=(8, 8))  # Adjust figure size
+plt.barh(emotions, frequencies, color="#84ade3")
+
+# Set x-axis limits
+plt.xlim(xlim)
+
+# Set x-axis ticks
+plt.xticks(xticks)
+
+# Set labels and title
+plt.xlabel(xlabel)
+plt.ylabel(ylabel)
+
+# ===================
+# Part 4: Saving Output
+# ===================
+# Show the plot with tight layout to minimize white space
+plt.tight_layout()
+plt.savefig("bar_6.pdf", bbox_inches="tight")

ChartMimic/dataset/ori_500/bar_65.py

@@ -0,0 +1,128 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import numpy as np
+
+np.random.seed(0)
+
+import matplotlib.pyplot as plt
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Define the categories and scores
+categories = ["LLAMA-Default", "LLAMA-HAG", "Vicuna-Default", "Vicuna-HAG"]
+num_scores = 4
+score_range = (-3.5, -0.5)
+scores_3 = np.random.uniform(score_range[0], score_range[1], num_scores).tolist()
+scores_5 = np.random.uniform(score_range[0], score_range[1], num_scores).tolist()
+scores_7 = np.random.uniform(score_range[0], score_range[1], num_scores).tolist()
+scores_10 = np.random.uniform(score_range[0], score_range[1], num_scores).tolist()
+
+# The x locations for the groups
+ind = np.arange(len(scores_3))
+
+# The width of the bars
+bar_width = 0.2
+
+# Labels and Plot Types
+label_3_Constraint_Words = "3 Constraint Words"
+label_5_Constraint_Words = "5 Constraint Words"
+label_7_Constraint_Words = "7 Constraint Words"
+label_10_Constraint_Words = "10 Constraint Words"
+
+# Axes Limits and Labels
+xlabel_value = "Score"
+ax_title = "Scores by group and constraint word count"
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+# Create the figure and axes objects
+fig, ax = plt.subplots(figsize=(10, 6))
+
+# Plotting data
+bars_3 = ax.barh(
+    ind - bar_width * 1.5,
+    scores_3,
+    bar_width,
+    label=label_3_Constraint_Words,
+    color="salmon",
+)
+bars_5 = ax.barh(
+    ind - bar_width * 0.5,
+    scores_5,
+    bar_width,
+    label=label_5_Constraint_Words,
+    color="skyblue",
+)
+bars_7 = ax.barh(
+    ind + bar_width * 0.5,
+    scores_7,
+    bar_width,
+    label=label_7_Constraint_Words,
+    color="coral",
+)
+bars_10 = ax.barh(
+    ind + bar_width * 1.5,
+    scores_10,
+    bar_width,
+    label=label_10_Constraint_Words,
+    color="lightblue",
+)
+
+# Adding text inside the bars
+for i, (score_3, score_5, score_7, score_10) in enumerate(
+    zip(scores_3, scores_5, scores_7, scores_10)
+):
+    ax.text(
+        score_3,
+        i - bar_width * 1.5,
+        f"{score_3:.1f}",
+        va="center",
+        ha="right",
+        color="black",
+    )
+    ax.text(
+        score_5,
+        i - bar_width * 0.5,
+        f"{score_5:.1f}",
+        va="center",
+        ha="right",
+        color="black",
+    )
+    ax.text(
+        score_7,
+        i + bar_width * 0.5,
+        f"{score_7:.1f}",
+        va="center",
+        ha="right",
+        color="black",
+    )
+    ax.text(
+        score_10,
+        i + bar_width * 1.5,
+        f"{score_10:.1f}",
+        va="center",
+        ha="right",
+        color="black",
+    )
+
+# Adding labels, title, and custom x-axis tick labels, etc.
+ax.set_xlabel(xlabel_value)
+ax.set_title(ax_title)
+ax.set_yticks(ind)
+ax.set_yticklabels(categories)
+ax.legend()
+
+# Invert y-axis to have the first entry at the top
+plt.gca().invert_yaxis()
+
+# Show grid lines for x-axis
+ax.xaxis.grid(True)
+
+# ===================
+# Part 4: Saving Output
+# ===================
+plt.tight_layout()
+plt.savefig("bar_65.pdf", bbox_inches="tight")

ChartMimic/dataset/ori_500/bar_89.py

@@ -0,0 +1,53 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Data for the bar chart
+superfamilies = range(1, 11)
+accuracies = [0.9, 0.83, 0.86, 0.84, 0.7, 0.85, 0.93, 0.89, 0.88, 1.0]
+accuracies2 = [0.3, 0.5, 0.8, 0.6, 0.4, 0.65, 0.43, 0.69, 0.58, 1.0]
+accuracies3 = [0.7, 0.6, 0.5, 0.7, 0.7, 0.64, 0.76, 0.56, 0.38, 1.0]
+xlabel = "Top-10 superfamilies in training dataset"
+ylabel1 = "Accuracy"
+ylabel2 = "Recall"
+ylabel3 = "Precision"
+ylim = [0.0, 1.1]
+yticks = [0.0, 0.2, 0.4, 0.6, 0.8, 1.0]
+yline = 0.6
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+# Create the bar chart
+fig, axes = plt.subplots(
+    3, 1, figsize=(10, 6), sharex=True
+)  # Adjusting figure size to match the original image's dimensions
+axes[0].bar(superfamilies, accuracies, color="#7fa9cc")
+axes[1].bar(superfamilies, accuracies2, color="#e39c90")
+axes[2].bar(superfamilies, accuracies3, color="#af86ce")
+
+# Add a horizontal line for the average accuracy
+axes[0].axhline(y=yline, color="red", linestyle="--")
+
+# Add labels and title
+plt.xlabel(xlabel)
+axes[0].set_ylabel(ylabel1)
+axes[1].set_ylabel(ylabel2)
+axes[2].set_ylabel(ylabel3)
+
+# Set y-axis limits
+plt.ylim(0.0, 1.1)
+# Set x-axis, y-axis ticks
+plt.xticks(superfamilies)
+plt.yticks([0.0, 0.2, 0.4, 0.6, 0.8, 1.0])
+
+# ===================
+# Part 4: Saving Output
+# ===================
+# Displaying the plot with tight layout to minimize white space
+plt.tight_layout()
+plt.savefig("bar_89.pdf", bbox_inches="tight")

ChartMimic/dataset/ori_500/bar_98.py

@@ -0,0 +1,91 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+import numpy as np
+
+np.random.seed(0)
+
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Data
+labels = [
+    "Model A",
+    "Model B",
+    "Model C",
+    "Model D",
+    "Model E",
+    "Model F",
+    "Model G",
+    "Model H",
+    "Model I",
+]
+non_aggregation = np.random.rand(9) * 100
+aggregation = np.random.rand(9) * 100
+
+datalabels = ["Contrastive Search", "Beam Search"]
+ylabel = "Scores"
+title = "Performance Comparison by Model"
+ylim = [0, 120]
+
+x = np.arange(len(labels))  # the label locations
+width = 0.35  # the width of the bars
+
+legendtitle = "Methods"
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+# Plotting
+fig, ax = plt.subplots(figsize=(10, 6))  # Adjust the size accordingly
+rects1 = ax.bar(
+    x - width / 2,
+    non_aggregation,
+    width,
+    label="Contrastive Search",
+    color="#69b3a2",
+    hatch="/",
+)
+rects2 = ax.bar(
+    x + width / 2, aggregation, width, label="Beam Search", color="#d98763", hatch="\\"
+)
+
+# Add some text for labels, title and custom x-axis tick labels, etc.
+ax.set_ylabel(ylabel)
+ax.set_title(title)
+ax.set_xticks(x)
+ax.set_xticklabels(labels, rotation=0)
+ax.set_ylim(ylim)
+ax.set_xlim(-1, len(labels))
+
+# Adding the values on top of the bars
+for rect in rects1 + rects2:
+    height = rect.get_height()
+    ax.annotate(
+        f"{height:.1f}",
+        xy=(rect.get_x() + rect.get_width() / 2, height),
+        xytext=(0, 3),  # 3 points vertical offset
+        textcoords="offset points",
+        ha="center",
+        va="bottom",
+    )
+
+# Custom grid
+ax.grid(axis="y", color="gray", linestyle="--", linewidth=0.7, alpha=0.7)
+ax.set_axisbelow(True)
+
+# Hide the ticks
+ax.tick_params(axis="both", which="both", length=0)
+
+# Hide the right and top spines
+ax.spines["right"].set_visible(False)
+ax.spines["top"].set_visible(False)
+ax.legend(title=legendtitle)
+
+# ===================
+# Part 4: Saving Output
+# ===================
+plt.tight_layout()
+plt.savefig("bar_98.pdf", bbox_inches="tight")

ChartMimic/dataset/ori_500/bar_99.py

@@ -0,0 +1,68 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+import numpy as np
+
+np.random.seed(0)
+
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Create traffic data
+data = np.array(
+    [
+        [150, 180, 75, 90, 80],  # Traffic flow (in thousands of vehicles per day)
+        [2.5, 2.0, 1.5, 2.0, 2.8],  # Accident rate (accidents per 100,000 vehicles)
+        [60, 55, 70, 65, 72],  # Public transport usage (% of population)
+        [80, 75, 90, 85, 88],  # Road conditions (road quality index out of 100)
+        [85, 80, 75, 90, 88],  # Public satisfaction (satisfaction score out of 100)
+    ]
+)
+categories = [
+    "Traffic Flow",
+    "Accident Rate",
+    "Public Transport Usage",
+    "Road Conditions",
+    "Public Satisfaction",
+]
+
+titles = ["Dataset 1", "Dataset 2", "Dataset 3", "Dataset 4"]
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+fig, axs = plt.subplots(2, 2, figsize=(10, 8))  # Creating a 2x2 grid of subplots
+
+colors = plt.get_cmap("Pastel2")(np.linspace(0.15, 0.85, data.shape[0]))
+bar_width = 0.5  # Width of the bars
+
+
+# Function to plot a bar chart in a specific subplot
+def plot_bars(ax, data, categories, color, title):
+    bars = ax.bar(np.arange(len(categories)), data, color=color, width=bar_width)
+    ax.set_title(title)
+    ax.set_xticks(np.arange(len(categories)))
+    ax.set_xticklabels(categories, rotation=45)
+    for bar in bars:
+        yval = bar.get_height()
+        ax.text(
+            bar.get_x() + bar.get_width() / 2.0,
+            yval,
+            round(yval, 1),
+            va="top",
+            ha="center",
+        )  # Annotate bars
+
+
+# Plot data on each subplot
+for i, ax in enumerate(axs.flat):
+    plot_bars(ax, data[i], categories, colors[i], titles[i])
+
+# ===================
+# Part 4: Saving Output
+# ===================
+# Adjust layout to prevent overlap
+fig.tight_layout()
+plt.savefig("bar_99.pdf", bbox_inches="tight")

ChartMimic/dataset/ori_500/box_13.py

@@ -0,0 +1,64 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+import numpy as np
+
+np.random.seed(0)
+
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Sample data to mimic the boxplot in the picture
+data = [
+    np.random.normal(0.825, 0.02, 100),
+    np.random.normal(0.850, 0.03, 100),
+    np.random.normal(0.840, 0.025, 100),
+    np.random.normal(0.860, 0.015, 100),
+    np.random.normal(0.855, 0.02, 100),
+]
+
+labels = ["SQL-Only", "PoT", "IC-LP", "DAIL", "IC-LP+PoT"]
+ylabel = "Execution Accuracy"
+ylim = [0.725, 0.925]
+yticks = np.arange(0.750, 0.901, 0.025)
+
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+# Create the boxplot
+fig, ax = plt.subplots(
+    figsize=(6, 5)
+)  # Adjusting figure size as per the dimensions provided
+bp = ax.boxplot(
+    data,
+    labels=labels,
+    patch_artist=True,
+    boxprops=dict(facecolor="#549e9a", color="black"),
+    medianprops=dict(color="black"),
+    whiskerprops=dict(color="black", linestyle="-"),
+    capprops=dict(color="black", linestyle="-"),
+)
+
+# Remove outliers
+for flier in bp["fliers"]:
+    flier.set(marker="", color="black")
+
+# Set the y-axis range and tick labels
+ax.set_ylim(ylim)
+ax.set_yticks(yticks)
+# Set the y-axis label
+ax.set_ylabel(ylabel, fontsize=12)
+
+# Set the tick label size
+ax.tick_params(axis="both", which="major", labelsize=10)
+plt.xticks(rotation=45)
+
+# ===================
+# Part 4: Saving Output
+# ===================
+# Displaying the plot with tight layout to minimize white space
+plt.tight_layout()
+plt.savefig("box_13.pdf", bbox_inches="tight")

ChartMimic/dataset/ori_500/errorbar_19.py

@@ -0,0 +1,76 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+import numpy as np
+
+np.random.seed(0)
+
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Data representing social statistics for three different cities
+categories = ["Detroit", "Philadelphia", "Baltimore"]
+metrics = [
+    "Crime Rate",
+    "Happiness Index",
+    "Social Security Coverage",
+    "Political Participation",
+]
+performance = np.array(
+    [
+        [50, 70, 90, 80],
+        [60, 80, 85, 75],
+        [40, 75, 95, 85],
+    ]
+)
+errors = np.array(
+    [
+        [5, 6, 9, 6],
+        [6, 7, 8, 7],
+        [8, 9, 6, 8],
+    ]
+)
+ylim = [30, 100]
+ylabel = "Percentage"
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+# Figure size to match a 3x1 subplot layout
+fig, axes = plt.subplots(3, 1, figsize=(10, 9), sharex=True)
+# Colors, choosing a different palette to differentiate the plots
+colors = ["#8e44ad", "#3498db", "#e74c3c", "#f1c40f"]
+
+# Plotting bars
+for i, ax in enumerate(axes):
+    for j, metric in enumerate(metrics):
+        ax.bar(
+            j,
+            performance[i, j],
+            width=0.8,
+            color=colors[j],
+            yerr=errors[i, j],
+            capsize=0,
+            label=metric if i == 0 else "",
+        )
+
+    # Setting x-axis labels, y-axis limits, and titles
+    ax.set_xticks(range(len(metrics)))
+    ax.set_xticklabels(metrics, rotation=45)
+    ax.set_ylim(ylim)
+    ax.set_xlabel(f"({chr(97+i)}) {categories[i]}")
+    ax.set_ylabel(ylabel)
+    ax.yaxis.grid(True)
+    ax.set_axisbelow(True)
+
+# Adding a legend outside of the plot on top
+fig.legend(loc="upper center", bbox_to_anchor=(0.5, 1.05), ncol=len(metrics))
+
+# ===================
+# Part 4: Saving Output
+# ===================
+# Adjusting layout to prevent overlap and ensure labels are visible
+plt.tight_layout()
+plt.savefig("errorbar_19.pdf", bbox_inches="tight")

ChartMimic/dataset/ori_500/errorbar_28.py

@@ -0,0 +1,82 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+import numpy as np
+
+np.random.seed(0)
+
+import matplotlib.colors as mcolors
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Data for environmental factors affecting plant growth
+categories = [
+    "Sunlight",
+    "Water Quality",
+    "Soil pH",
+    "Fertilizer",
+    "Temperature",
+    "Pesticides",
+    "CO2 Levels",
+    "Plant Variety",
+    "Planting Density",
+    "Watering Frequency",
+]
+values = [0.18, 0.15, 0.12, 0.09, 0.06, 0.03, -0.06, -0.03, -0.02, -0.03]
+errors = [0.05, 0.04, 0.03, 0.03, 0.02, 0.02, 0.02, 0.02, 0.01, 0.01]
+
+min_val = min(values) - 0.1
+max_val = max(values) + 0.1
+
+
+# Normalizing function to convert values to a 0-1 range for color scaling
+def normalize(value, min_val, max_val):
+    return (value - min_val) / (max_val - min_val)
+
+
+# Determine color based on normalized value
+def get_color(value):
+    norm_value = normalize(value, min_val, max_val)
+    green_base = np.array(mcolors.to_rgb("#6a8347"))
+    # Create a color that ranges from very light green to the base green
+    return mcolors.to_hex((1 - green_base) * (1 - norm_value) + green_base)
+
+
+colors = [get_color(value) for value in values]
+
+# Axes Limits and Labels
+ylabel_value = "Environmental Factors"
+xlabel_value = "Impact on Plant Growth (Δ to control)"
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+# Create figure and axis
+fig, ax = plt.subplots(figsize=(10, 8))
+
+# Horizontal bar chart
+bars = ax.barh(
+    categories, values, xerr=errors, color=colors, capsize=3, edgecolor="none"
+)
+ax.set_ylabel(ylabel_value)
+ax.set_xlabel(xlabel_value)
+
+# Set y-axis limits and x-axis limits
+ax.set_xlim(min_val, max_val)  # Adjust limits to encompass errors
+
+# Remove top and right spines for a cleaner look
+ax.spines["top"].set_visible(False)
+ax.spines["right"].set_visible(False)
+
+# Customize grid lines
+ax.xaxis.grid(True, linestyle="--", which="major", color="gray", alpha=0.6)
+ax.set_axisbelow(True)
+
+# ===================
+# Part 4: Saving Output
+# ===================
+# Adjust layout to prevent clipping of ylabel
+plt.tight_layout()
+plt.savefig("errorbar_28.pdf", bbox_inches="tight")

ChartMimic/dataset/ori_500/errorbar_29.py

@@ -0,0 +1,83 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+import numpy as np
+
+np.random.seed(0)
+
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Updated Urban Transportation Data for three major cities
+metrics = ["Traffic Volume", "Public Transit", "Accident Rate"]
+values = np.array(
+    [
+        [220, 180, 220],  # New York
+        [150, 120, 130],  # Los Angeles
+        [130, 160, 110],  # Chicago
+    ]
+)
+
+# Updated asymmetric error values, now more proportionate to the data scale
+errors = np.array(
+    [
+        [[25, 20], [15, 15], [25, 20]],  # Errors for New York (lower, upper)
+        [[20, 15], [10, 15], [20, 10]],  # Errors for Los Angeles
+        [[15, 20], [15, 10], [15, 15]],  # Errors for Chicago
+    ]
+)
+
+# Creating subplots for each city
+cities = ["New York", "Los Angeles", "Chicago"]
+
+ylabel = "Metric Values"
+ylim = [80, 280]
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+fig, axs = plt.subplots(1, 3, figsize=(10, 4))  # Compact and square figure layout
+
+
+# Function to plot each city's data
+def plot_city_data(ax, errors, city_index, city_name):
+    x = np.arange(len(metrics))  # the label locations
+    bar_colors = ["#6a8347", "#377eb8", "#d62728"]
+    barerrors = np.array(errors).T[:, :, city_index]
+    bars = ax.bar(x, values[city_index], yerr=barerrors, color=bar_colors, capsize=5)
+    for bar, lower_error, upper_error in zip(bars, barerrors[0], barerrors[1]):
+        # Position for lower error text
+        ax.text(
+            bar.get_x() + bar.get_width() / 2,
+            bar.get_height() - lower_error - 15,
+            f"-{lower_error}",
+            va="bottom",
+            ha="center",
+            color="black",
+        )
+        # Position for upper error text
+        ax.text(
+            bar.get_x() + bar.get_width() / 2,
+            bar.get_height() + upper_error + 3,
+            f"+{upper_error}",
+            ha="center",
+            color="black",
+        )
+
+    ax.set_title(city_name)
+    ax.set_xticks(x)
+    ax.set_xticklabels(metrics, rotation=90)
+    ax.set_ylabel(ylabel)
+    ax.set_ylim(ylim)  # Uniform scale for all charts
+
+
+for i, city in enumerate(cities):
+    plot_city_data(axs[i], errors, i, city)
+
+# ===================
+# Part 4: Saving Output
+# ===================
+plt.tight_layout()
+plt.savefig("errorbar_29.pdf", bbox_inches="tight")

ChartMimic/dataset/ori_500/errorbar_8.py

@@ -0,0 +1,88 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+import numpy as np
+
+np.random.seed(0)
+
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Data (estimated from the image)
+models = [
+    "BERT",
+    "RoBERTa",
+    "DistilBERT",
+    "XLNet",
+    "Electra",
+    "Albert",
+    "BART",
+    "DeBERTa",
+    "Llama2",
+]
+ground_truth_accuracy = [50, 55, 60, 65, 40, 30, 70, 45, 35]
+weak_labels_accuracy = [45, 50, 55, 60, 35, 25, 65, 40, 30]
+error = [10, 8, 12, 10, 5, 7, 8, 10, 5]
+labels = ["Ground-truth labels", "Weak labels"]
+ylabel = "Accuracy (%)"
+ylim = [0, 80]
+yticks = np.arange(0, 71, 10)
+
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+fig = plt.subplots(figsize=(10, 3))
+# Bar width
+bar_width = 0.35
+
+# X position of bars
+r1 = np.arange(len(ground_truth_accuracy))
+r2 = [x + bar_width for x in r1]
+
+# Create bars
+plt.bar(
+    r1,
+    ground_truth_accuracy,
+    color="#d47e6d",
+    width=bar_width,
+    label=labels[0],
+    yerr=error,
+    capsize=7,
+)
+plt.bar(
+    r2,
+    weak_labels_accuracy,
+    color="#76a4c5",
+    width=bar_width,
+    label=labels[1],
+    yerr=error,
+    capsize=7,
+)
+
+# Add xticks on the middle of the group bars
+plt.xticks([r + bar_width / 2 for r in range(len(ground_truth_accuracy))], models)
+
+# Create legend & Show graphic
+plt.ylabel(ylabel)
+plt.legend(frameon=False, loc="upper right")  # Remove legend background
+
+# Set background color and grid
+plt.gca().set_facecolor("#e5e5e5")
+plt.grid(color="white", linestyle="-", linewidth=0.25, axis="both")
+plt.gca().set_axisbelow(True)
+
+# Set y-axis limits
+plt.ylim(ylim)
+plt.yticks(yticks)
+
+for spine in plt.gca().spines.values():
+    spine.set_visible(False)
+
+# ===================
+# Part 4: Saving Output
+# ===================
+plt.tight_layout()
+plt.savefig("errorbar_8.pdf", bbox_inches="tight")

ChartMimic/dataset/ori_500/errorbar_9.py

@@ -0,0 +1,64 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Categories and values (estimated from the image)
+categories = [
+    "Syntax: Tagging, Chunking and Parsing",
+    "Discourse and Pragmatics",
+    "Information Extraction",
+    "Machine Learning for NLP",
+    "Information Retrieval and Text Mining",
+    "Phonology, Morphology and Word Segmentation",
+    "Computational Social Science and Social Media",
+][::-1]
+values = [-3.20, -3.1, -3.00, -2.90, -2.80, -2.70, -2.60][::-1]
+error = [0.1, 0.15, 0.3, 0.25, 0.2, 0.1, 0.05]
+xlabel = "A"
+ylabel = "Categories"
+title = "Your Chart Title Here"
+xlim = [-3.5, -1.5]
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+# Create horizontal bar chart
+fig, ax = plt.subplots(figsize=(8, 8))  # Adjust figure size
+bars = ax.barh(
+    categories,
+    values,
+    color="#c5b3d6",
+    edgecolor="white",
+    height=0.5,
+    xerr=error,
+    capsize=0,
+)
+
+# Set labels and title (if any)
+ax.set_xlabel(xlabel)
+ax.set_ylabel(ylabel)
+ax.set_title(title)
+
+# Invert y-axis to match the image
+ax.invert_yaxis()
+
+# Set x-axis range to match the reference image
+ax.set_xlim(xlim)
+
+# Remove grid lines
+ax.xaxis.grid(False)
+ax.spines["top"].set_visible(False)
+ax.spines["right"].set_visible(False)
+
+# Set background color to white
+ax.set_facecolor("white")
+
+# ===================
+# Part 4: Saving Output
+# ===================
+# Displaying the plot with tight layout to minimize white space
+plt.tight_layout()
+plt.savefig("errorbar_9.pdf", bbox_inches="tight")

ChartMimic/dataset/ori_500/errorpoint_1.py

@@ -0,0 +1,66 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+import numpy as np
+
+np.random.seed(0)
+
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Sample data (replace with actual data)
+categories = [
+    "Kashmir",
+    "Religion",
+    "Crime and Justice",
+    "CAA",
+    "Pulwama-Balakot",
+    "Politics",
+]
+means = np.random.uniform(0.05, 0.15, len(categories))
+std_devs = np.random.uniform(0.01, 0.05, len(categories))
+dataset_mean = np.mean(means)
+
+# Labels and Plot Types
+label_Mean = "Mean"
+label_Dataset_mean = "Dataset mean"
+
+# Axes Limits and Labels
+ylabel_value = "Shouting Fraction (Fraction of videos)"
+ylim_values = [0.01, 0.18]
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+# Create figure and axis
+fig, ax = plt.subplots(figsize=(8, 5))
+
+# Error bar plot
+ax.errorbar(
+    categories,
+    means,
+    yerr=std_devs,
+    fmt="o",
+    color="blue",
+    ecolor="blue",
+    capsize=5,
+    label=label_Mean,
+)
+
+# Dataset mean line
+ax.axhline(y=dataset_mean, color="grey", linestyle="--", label=label_Dataset_mean)
+
+# Customizing the plot
+ax.set_ylabel(ylabel_value)
+ax.set_xticklabels(categories, rotation=45, ha="right")
+ax.legend()
+ax.set_ylim(ylim_values)
+
+# ===================
+# Part 4: Saving Output
+# ===================
+# Adjust layout to prevent clipping of tick-labels
+plt.tight_layout()
+plt.savefig("errorpoint_1.pdf", bbox_inches="tight")

ChartMimic/dataset/ori_500/errorpoint_4.py

@@ -0,0 +1,72 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Data (example values, replace with actual data)
+categories = [
+    "Education",
+    "Religion",
+    "Bollywood",
+    "Crime and Justice",
+    "Farmers Protest",
+    "Issue Politics",
+]
+unique_speaker_mean = [10, 12, 11, 13, 14, 15]  # Replace with actual mean values
+unique_shouter_mean = [5, 6, 7, 6, 5, 4]  # Replace with actual mean values
+unique_speaker_error = [1, 1.5, 1, 1.5, 2, 1.5]  # Replace with actual error values
+unique_shouter_error = [
+    0.5,
+    0.75,
+    0.5,
+    0.75,
+    1,
+    0.75,
+]  # Replace with actual error values
+labels = ["Unique speaker count mean", "Unique shouter count mean"]
+ylabel = "Number of speakers"
+axlabel = "Dataset unique shouter count mean"
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+# Plotting
+fig, ax = plt.subplots(
+    figsize=(10, 6)
+)  # Adjust the size to match the original image's dimensions
+ax.errorbar(
+    categories,
+    unique_speaker_mean,
+    yerr=unique_speaker_error,
+    fmt="o",
+    color="blue",
+    label=labels[0],
+)
+ax.errorbar(
+    categories,
+    unique_shouter_mean,
+    yerr=unique_shouter_error,
+    fmt="o",
+    color="red",
+    label=labels[1],
+)
+
+# Customization
+ax.set_ylabel(ylabel)
+ax.set_xticklabels(categories, rotation=45, ha="right")
+ax.axhline(
+    y=sum(unique_shouter_mean) / len(unique_shouter_mean),
+    color="grey",
+    linestyle="--",
+    label=axlabel,
+)
+ax.legend()
+
+# ===================
+# Part 4: Saving Output
+# ===================
+# Show plot
+plt.tight_layout()
+plt.savefig("errorpoint_4.pdf", bbox_inches="tight")

ChartMimic/dataset/ori_500/errorpoint_5.py

@@ -0,0 +1,77 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Data for plotting
+categories = [
+    "KASHMIR",
+    "COVID/LOCKDOWN",
+    "SPORTS",
+    "CHINA",
+    "PULWAMA-BALAKOT",
+]  # Capitalized category labels
+means = [0.22, 0.23, 0.18, 0.12, 0.05]
+errors = [0.03, 0.02, 0.05, 0.06, 0.02]
+downerrors = [0.01, 0.02, 0.03, 0.04, 0.05]
+legendtitles = ["Dataset mean", "Mean"]
+texttitle = "Dataset mean"
+ylabel = "Female Face presence (Fraction of videos)"
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+# Plotting the data
+fig, ax = plt.subplots(
+    figsize=(8, 6)
+)  # Adjusting figure size to match original image dimensions
+ax.errorbar(
+    categories,
+    means,
+    yerr=[errors, downerrors],
+    fmt="o",
+    color="blue",
+    ecolor="blue",
+    capsize=5,
+)
+
+# Adding a legend with both "Mean" and "Dataset mean"
+dataset_mean = 0.253
+mean_line = ax.errorbar(
+    [], [], yerr=[], fmt="o", color="blue", ecolor="blue", capsize=5
+)
+dataset_mean_line = ax.axhline(
+    y=dataset_mean, color="gray", linestyle="--", linewidth=1
+)
+ax.legend(
+    [dataset_mean_line, mean_line],
+    legendtitles,
+    loc="upper right",
+    fancybox=True,
+    framealpha=1,
+    shadow=True,
+    borderpad=1,
+)
+# Adding a horizontal line for dataset mean and text annotation with a white background
+ax.text(
+    0.95,
+    dataset_mean,
+    texttitle,
+    va="center",
+    ha="right",
+    backgroundcolor="white",
+    transform=ax.get_yaxis_transform(),
+)
+# Setting labels
+ax.set_ylabel(ylabel)
+ax.set_title("")
+plt.xticks(rotation=30)
+
+# ===================
+# Part 4: Saving Output
+# ===================
+plt.tight_layout()
+plt.savefig("errorpoint_5.pdf", bbox_inches="tight")

ChartMimic/dataset/ori_500/graph_2.py

@@ -0,0 +1,50 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+import networkx as nx
+import numpy as np
+
+np.random.seed(0)
+
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Create a random graph
+G = nx.random_geometric_graph(30, 0.3)
+
+# Position the nodes based on their connections using a different layout algorithm
+pos = nx.kamada_kawai_layout(
+    G
+)  # This layout algorithm may produce a more spread-out layout
+
+# Randomly select some edges to color blue
+edges = list(G.edges())
+blue_edges = np.random.choice(
+    len(edges), size=int(len(edges) * 0.3), replace=False
+)  # 30% of the edges
+blue_edges = [edges[i] for i in blue_edges]
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+fig = plt.subplots(figsize=(8, 8))
+
+# Draw the nodes
+nx.draw_networkx_nodes(G, pos, node_size=200, node_color="pink")
+
+# Draw the edges
+nx.draw_networkx_edges(G, pos, alpha=0.3)
+
+# Draw the selected edges in blue
+nx.draw_networkx_edges(G, pos, edgelist=blue_edges, edge_color="#d0e2e8")
+
+# Remove axis
+plt.axis("off")
+
+# ===================
+# Part 4: Saving Output
+# ===================
+plt.tight_layout()
+plt.savefig("graph_2.pdf", bbox_inches="tight")

ChartMimic/dataset/ori_500/graph_3.py

@@ -0,0 +1,35 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+import networkx as nx
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Create a cycle graph with 12 nodes
+G = nx.cycle_graph(12)
+weights = {edge: i + 1 for i, edge in enumerate(G.edges())}
+nx.set_edge_attributes(G, weights, "weight")
+
+pos = nx.spring_layout(G, iterations=200)
+
+labels = {i: str(i) for i in range(12)}
+
+# Draw edge labels
+edge_labels = nx.get_edge_attributes(G, "weight")
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+plt.figure(figsize=(10, 8))
+nx.draw(G, pos, node_size=800, node_color="gold")
+nx.draw_networkx_labels(G, pos, labels=labels)
+nx.draw_networkx_edge_labels(G, pos, edge_labels=edge_labels)
+
+# ===================
+# Part 4: Saving Output
+# ===================
+# Show the plot
+plt.tight_layout()
+plt.savefig("graph_3.pdf", bbox_inches="tight")

ChartMimic/dataset/ori_500/hist_15.py

@@ -0,0 +1,57 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+import numpy as np
+
+np.random.seed(0)
+
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Generate normally distributed data
+data = np.random.normal(loc=2.0, scale=1.0, size=10000)
+
+# Axes Limits and Labels
+title = "Histogram of Wind Speed Measurements"
+xlabel_value = "Wind Speed (km/h)"
+ylabel_value = "Number of Measurements"
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+# Set the figure size
+plt.figure(figsize=(8, 6))
+
+# Enable the grid
+plt.grid(True, linestyle="--", linewidth=0.5, alpha=0.7)
+
+# Histogram of the data
+n, bins, patches = plt.hist(data, bins=25, color="skyblue", edgecolor="blue", alpha=0.7)
+
+# Highlight the median of the data
+median = np.median(data)
+plt.axvline(median, color="purple", linestyle="dashed", linewidth=2)
+
+# Adjust the median text position to not overlap the bars when possible
+median_text_position = max(n) * 0.9
+for bin_edge, count in zip(bins, n):
+    if bin_edge > median and count < median_text_position:
+        # Place the text above the median position
+        median_text_position = count
+        break
+plt.text(median + 0.5, median_text_position, f"Median: {median:.2f}", color="purple")
+
+# Title and labels relevant to database statistics
+plt.title(title)
+plt.xlabel(xlabel_value)
+plt.ylabel(ylabel_value)
+
+# ===================
+# Part 4: Saving Output
+# ===================
+# Adjust the layout
+plt.tight_layout()
+
+plt.savefig("hist_15.pdf", bbox_inches="tight")

ChartMimic/dataset/ori_500/hist_4.py

@@ -0,0 +1,91 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+import numpy as np
+
+np.random.seed(0)
+
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Sample data (replace with actual data)
+center_data = np.random.normal(6, 2, 1000)
+random_data = np.random.normal(1, 2, 1000)
+
+# Define bins aligned for both histograms
+bins = np.histogram(np.hstack((center_data, random_data)), bins=30)[1]
+labels = ["Center", "Random"]
+xlabel = "Distance Difference (Random vs. Center)"
+ylabel = "Number of Examples"
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+# Create figure and axis
+fig, ax = plt.subplots(
+    figsize=(5, 3)
+)  # Adjusted to match the original image's dimensions
+
+# Calculate the histogram data for each set and plot them
+ax.hist(
+    center_data,
+    bins=bins,
+    color="#f2a965",
+    edgecolor="#fdf460",
+    linewidth=1.2,
+    label=labels[0],
+    align="mid",
+    histtype="stepfilled",
+    alpha=0.7,
+)
+ax.hist(
+    random_data,
+    bins=bins,
+    color="#709dc6",
+    edgecolor="#ca3531",
+    linewidth=1.2,
+    label=labels[1],
+    align="mid",
+    histtype="stepfilled",
+    alpha=0.7,
+)
+
+# To show the overlapping areas, we plot the two histograms with transparency
+ax.hist(
+    center_data,
+    bins=bins,
+    color="#f2a965",
+    edgecolor="#fdf460",
+    linewidth=1.2,
+    alpha=0.7,
+    align="mid",
+    histtype="stepfilled",
+)
+ax.hist(
+    random_data,
+    bins=bins,
+    color="#709dc6",
+    edgecolor="#ca3531",
+    linewidth=1.2,
+    alpha=0.7,
+    align="mid",
+    histtype="stepfilled",
+)
+
+# Set labels
+ax.set_xlabel(xlabel)
+ax.set_ylabel(ylabel)
+
+# Add legend
+ax.legend()
+
+# ===================
+# Part 4: Saving Output
+# ===================
+# Adjust layout
+plt.tight_layout()
+
+# Save the plot
+plt.savefig("hist_4.pdf", bbox_inches="tight")

ChartMimic/dataset/ori_500/hist_5.py

@@ -0,0 +1,53 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+import numpy as np
+
+np.random.seed(0)
+
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Sample data to approximate the distribution in the image
+data = np.random.gamma(shape=2.0, scale=1.0, size=10000)
+data = data[data < 30]  # Limiting the data to match the x-axis in the image
+xlabel = "Number of Repetition"
+ylabel = "Number of Clusters"
+binslist = [30, 30]
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+# Set the figure size to match the original image's dimensions
+plt.figure(figsize=(4, 3))
+
+# Show grid with some transparency
+plt.grid(True, linestyle="-", linewidth=0.5, color="#000000", alpha=0.1)
+
+# Create the histogram
+plt.hist(data, bins=binslist[0], color="#dca684")
+
+# Create the histogram with histtype='step' for edge-only bars
+plt.hist(
+    data,
+    bins=binslist[1],
+    color="#dca684",
+    edgecolor="#d1885c",
+    histtype="step",
+    linewidth=1.2,
+)
+
+# Set the title and labels to match the image
+plt.xlabel(xlabel)
+plt.ylabel(ylabel)
+
+# ===================
+# Part 4: Saving Output
+# ===================
+# Adjust layout
+plt.tight_layout()
+
+# Display the plot
+plt.savefig("hist_5.pdf", bbox_inches="tight")

ChartMimic/dataset/ori_500/line_12.py

@@ -0,0 +1,103 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+
+import matplotlib.pyplot as plt
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Data for plotting
+sample_ratio = [0.25, 0.50, 0.75, 1.00]
+std_acc_512 = [0.07, 0.06, 0.01, 0.05]
+std_acc_1024 = [0.055, 0.045, 0.04, 0.035]
+std_acc_2048 = [0.03, 0.025, 0.02, 0.015]
+
+# Extracted variables
+line_label_512 = "MAXN=512"
+line_label_1024 = "MAXN=1024"
+line_label_2048 = "MAXN=2048"
+xlim_values = (0.25, 1)
+ylim_values = (0.00, 0.08)
+xlabel_value = "Sample Ratio"
+ylabel_value = "Std of ACC"
+xticks_values = sample_ratio
+yticks_values = None  # Not explicitly set in the code
+xtickslabel_fontsize = 14
+ytickslabel_fontsize = 14
+title_value = None  # Not explicitly set in the code
+axhline_value = None  # Not explicitly set in the code
+axvline_value = None  # Not explicitly set in the code
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+# Plotting the lines with increased marker size and line width
+plt.figure(figsize=(8, 6))
+plt.plot(
+    sample_ratio,
+    std_acc_512,
+    marker="*",
+    markersize=10,
+    linewidth=2,
+    color="#2ab34a",
+    label=line_label_512,
+    clip_on=False,
+    zorder=10,
+)
+plt.plot(
+    sample_ratio,
+    std_acc_1024,
+    marker="^",
+    markerfacecolor="white",
+    markersize=10,
+    linewidth=2,
+    markeredgecolor="#ee756e",
+    color="#ee756e",
+    clip_on=False,
+    zorder=10,
+    label=line_label_1024,
+)
+plt.plot(
+    sample_ratio,
+    std_acc_2048,
+    marker="o",
+    markerfacecolor="white",
+    markersize=10,
+    linewidth=2,
+    markeredgecolor="#4995c6",
+    color="#4995c6",
+    clip_on=False,
+    zorder=10,
+    label=line_label_2048,
+)
+
+# Setting the x-axis and y-axis limits
+plt.ylim(*ylim_values)  # Set y-axis to go from 0 to 7
+plt.yticks(fontsize=ytickslabel_fontsize)
+plt.xlim(*xlim_values)  # Set y-axis to go from 0 to 7
+# Set x-axis to show only the values in the sample_ratio list
+plt.xticks(xticks_values, fontsize=xtickslabel_fontsize)
+
+# Adding labels and title
+plt.xlabel(xlabel_value, fontsize=18)
+plt.ylabel(ylabel_value, fontsize=18)
+
+# Adding legend with increased font size
+plt.legend(
+    fontsize="large",
+    loc="upper center",
+    ncol=3,
+    frameon=False,
+    bbox_to_anchor=(0.5, 1.1),
+)
+
+# Adding grid
+plt.grid(True, alpha=0.6)
+
+# ===================
+# Part 4: Saving Output
+# ===================
+# Adjusting layout to reduce white space
+plt.tight_layout()
+plt.savefig('line_12.pdf', bbox_inches='tight')

ChartMimic/dataset/ori_500/line_18.py

@@ -0,0 +1,105 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+import numpy as np; np.random.seed(0)
+
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Sample data
+iterations = np.array([0, 250, 500, 750, 1000, 1250, 1500, 1750, 2000])
+gpt4_7b = np.array([0.1, 0.4, 0.7, 0.85, 0.9, 0.92, 0.93, 0.94, 0.95])
+gpt4_7b_ft = np.array([0.05, 0.2, 0.35, 0.5, 0.6, 0.65, 0.7, 0.72, 0.73])
+llama_7b = np.array([0.1, 0.45, 0.75, 0.88, 0.9, 0.91, 0.92, 0.93, 0.94])
+llama_7b_ft = np.array([0.05, 0.25, 0.4, 0.55, 0.65, 0.7, 0.75, 0.77, 0.78])
+
+# Axes Limits and Labels
+xlabel_value = "Iterations"
+ylabel_value = "Attack Success Rate"
+
+# Labels
+label_1 = "7B"
+label_2 = "7B (Fine-tuned)"
+
+# Titles
+title_1 = "GPT-4 Evaluation"
+title_2 = "Llama Guard Evaluation"
+
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+# Set the figure size to match the original image's dimensions
+plt.figure(figsize=(9, 4))
+
+# First subplot
+plt.subplot(1, 2, 1)
+plt.plot(
+    iterations,
+    gpt4_7b,
+    marker="o",
+    color="#0a6ae1",
+    label=label_1,
+    markerfacecolor="#0a6ae1",
+    linewidth=2,
+    markersize=5,
+)
+plt.plot(
+    iterations,
+    gpt4_7b_ft,
+    marker="o",
+    color="#d75faa",
+    label=label_2,
+    markerfacecolor="#d75faa",
+    linewidth=2,
+    markersize=5,
+)
+plt.fill_between(iterations, gpt4_7b - 0.05, gpt4_7b + 0.05, color="#0a6ae1", alpha=0.2)
+plt.fill_between(
+    iterations, gpt4_7b_ft - 0.03, gpt4_7b_ft + 0.03, color="#d75faa", alpha=0.2
+)
+plt.title(title_1, fontsize=14)
+plt.xlabel(xlabel_value, fontsize=12)
+plt.ylabel(ylabel_value, fontsize=12)
+
+# Second subplot
+plt.subplot(1, 2, 2)
+plt.plot(
+    iterations,
+    llama_7b,
+    marker="o",
+    color="#0a6ae1",
+    label=label_1,
+    markerfacecolor="#0a6ae1",
+    linewidth=2,
+    markersize=5,
+)
+plt.plot(
+    iterations,
+    llama_7b_ft,
+    marker="o",
+    color="#d75faa",
+    label=label_2,
+    markerfacecolor="#d75faa",
+    linewidth=2,
+    markersize=5,
+)
+plt.fill_between(
+    iterations, llama_7b - 0.05, llama_7b + 0.05, color="#0a6ae1", alpha=0.2
+)
+plt.fill_between(
+    iterations, llama_7b_ft - 0.03, llama_7b_ft + 0.03, color="#d75faa", alpha=0.2
+)
+plt.title(title_2, fontsize=14)
+plt.xlabel(xlabel_value, fontsize=12)
+plt.ylabel(ylabel_value, fontsize=12)
+plt.legend(loc="lower right", frameon=True, bbox_to_anchor=(1, 0.1))
+
+# ===================
+# Part 4: Saving Output
+# ===================
+# Adjust layout and save plot
+plt.tight_layout()
+plt.savefig('line_18.pdf', bbox_inches='tight')

ChartMimic/dataset/ori_500/line_19.py

@@ -0,0 +1,64 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+import numpy as np; np.random.seed(0)
+
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Data for plotting
+fraction_of_training_data = np.array([0.01, 0.1, 1])
+full_accuracy = np.array([60, 70, 80])
+spt_accuracy = np.array([55, 65, 78])
+vpt_accuracy = np.array([42, 53, 65])
+
+# Axes Limits and Labels
+xlabel_value = "fraction of training data (log scale)"
+xlim_values = [5, 25]
+
+ylabel_value = "test accuracy (%)"
+ylim_values = [38, 84]
+yticks_values = np.arange(40, 82, 10)
+
+# Labels
+label_Full = "Full"
+label_SPT = "SPT"
+label_VPT = "VPT"
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+# Plotting the data
+plt.figure(figsize=(5, 4))  # Adjusting figure size to match original image dimensions
+plt.plot(fraction_of_training_data, full_accuracy, "o-", color="green", label=label_Full)
+plt.plot(fraction_of_training_data, spt_accuracy, "o-", color="red", label=label_SPT)
+plt.plot(fraction_of_training_data, vpt_accuracy, "o-", color="blue", label=label_VPT)
+
+# Set y-axis to only display specific ticks and extend y-axis to leave space at top
+plt.yticks(yticks_values, fontsize=16)
+plt.ylim(ylim_values)  # Adjusted y-axis limit
+
+# Set x-axis fontsize
+plt.xticks(fontsize=16)
+
+# Setting the x-axis to log scale
+plt.xscale("log")
+
+# Adding labels and title
+plt.xlabel(xlabel_value, fontsize=16)
+plt.ylabel(ylabel_value, fontsize=16)
+
+# Adding grid
+plt.grid(True, which="both", ls="-", linewidth=0.8)
+
+# Adding legend, show it horizontally and place it at the lower right corner
+plt.legend(loc="lower right", fontsize=12, ncol=3, columnspacing=0.5, edgecolor="black")
+
+# ===================
+# Part 4: Saving Output
+# ===================
+# Adjusting layout to add more space on the right
+plt.tight_layout()
+plt.savefig('line_19.pdf', bbox_inches='tight')

ChartMimic/dataset/ori_500/line_26.py

@@ -0,0 +1,100 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+
+import matplotlib.pyplot as plt
+import numpy as np; np.random.seed(0)
+
+from matplotlib.ticker import MultipleLocator
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Data for plotting
+vocab_sizes = ["256", "512", "1024", "2048", "4096", "8192", "16384"]
+bpe_values = [0.4, 0.8, 0.9, 0.95, 0.95, 0.95, 0.95]
+wordpunct_values = [0.3, 0.6, 0.8, 0.85, 0.9, 0.9, 0.9]
+whitespace_values = [0.5, 0.65, 0.7, 0.75, 0.7, 0.65, 0.6]
+
+# Variables for plot configuration
+line_labels = ["BPE", "Wordpunct", "Whitespace"]
+xlim_values = (0, len(vocab_sizes) - 1)
+ylim_values = (0.2, 1.0)
+xlabel_value = "Vocabulary Size"
+ylabel_value = None
+xticks_values = range(len(vocab_sizes))
+yticks_values = np.arange(0.2, 1.1, 0.2)
+xtickslabel_values = vocab_sizes
+ytickslabel_values = None
+title_value = "Test set TPR | FPR = $10^{-4}$"
+axhline_value = None
+axvline_value = None
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+# Plotting the lines
+plt.figure(figsize=(8, 6))
+plt.plot(
+    vocab_sizes,
+    bpe_values,
+    "o--",
+    clip_on=False,
+    zorder=10,
+    color="#0c5da5",
+    label=line_labels[0],
+)
+plt.plot(
+    vocab_sizes,
+    wordpunct_values,
+    "o--",
+    clip_on=False,
+    zorder=10,
+    color="#ff9500",
+    label=line_labels[1],
+)
+plt.plot(
+    vocab_sizes,
+    whitespace_values,
+    "o--",
+    clip_on=False,
+    zorder=10,
+    color="#00b945",
+    label=line_labels[2],
+)
+
+# Setting x and y ticks
+plt.xticks(xticks_values, xtickslabel_values, fontsize=14)
+plt.xlim(xlim_values)
+plt.yticks(yticks_values, fontsize=14)
+
+# Adding minor y-axis ticks with a step of 0.05
+ax = plt.gca()
+# ax.yaxis.set_minor_locator(MultipleLocator(0.05))
+
+# Adjust tick parameters
+ax.tick_params(axis="both", which="both", length=5, color="gray")  # Move ticks inside
+ax.tick_params(
+    axis="y", which="minor", length=2
+)  # Ensure minor ticks are visible but smaller
+
+# Title and labels
+plt.title(title_value, fontsize=14)
+plt.xlabel(xlabel_value, fontsize=14)
+
+# Enable gridlines for minor ticks
+plt.grid(True, color="#b0b0b0", which="major", linestyle="-", linewidth=0.5)
+
+# Legend with serif font family
+plt.legend(
+    frameon=False, fontsize=12, loc="lower center", bbox_to_anchor=(0.5, -0.2), ncol=3
+)
+
+# ===================
+# Part 4: Saving Output
+# ===================
+# Adjusting layout to add more space on the right
+plt.tight_layout()
+
+plt.savefig('line_26.pdf', bbox_inches='tight')
+

ChartMimic/dataset/ori_500/line_28.py

@@ -0,0 +1,70 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+import numpy as np; np.random.seed(0)
+
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Data
+x = [0, 25, 50, 75, 100, 125, 150, 175, 200]
+pilote_y = [0.85, 0.88, 0.90, 0.92, 0.93, 0.94, 0.80, 0.75, 0.70]
+retrained_y = [0.78, 0.80, 0.83, 0.85, 0.87, 0.88, 0.89, 0.90, 0.91]
+pretrained_accuracy = 0.75
+
+# Axes Limits and Labels
+xlabel_value = "Number of exemplars in class 'Run'"
+xlim_values = [-10, 215]
+xticks_values = np.arange(25, 201, 25)
+
+ylabel_value = "avg. accuracy of five rounds"
+ylim_values = [0, 100]
+yticks_values = np.arange(0.60, 1.00, 0.05)
+
+# Labels
+label_1 = "PILOTE"
+label_2 = "Re-trained model"
+label_3 = "Pre-trained model accuracy"
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+# Plot
+fig, ax = plt.subplots(
+    figsize=(6, 4)
+)  # Adjusting figure size to match original image dimensions
+
+# Line charts
+ax.plot(x, pilote_y, marker="s", color="#d62728", label=label_1)
+ax.plot(
+    x, retrained_y, marker="p", color="#1f77b4", label=label_2, markersize=8
+)
+
+# Set x,y-axis to only display specific ticks and extend y-axis to leave space at top
+plt.yticks(yticks_values, fontsize=12)
+plt.xticks(xticks_values, fontsize=12)
+plt.xlim(xlim_values)  # Adjusted y-axis limit
+
+# Horizontal dashed line
+ax.axhline(
+    y=pretrained_accuracy,
+    color="green",
+    linestyle="-.",
+    label=label_3,
+)
+
+# Legend
+ax.legend(loc="lower right")
+
+# Labels
+ax.set_xlabel(xlabel_value)
+ax.set_ylabel(ylabel_value)
+
+# ===================
+# Part 4: Saving Output
+# ===================
+# Adjust layout and show plot
+plt.tight_layout()
+plt.savefig('line_28.pdf', bbox_inches='tight')

ChartMimic/dataset/ori_500/line_29.py

@@ -0,0 +1,70 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Data for plotting
+xllm_steps = range(1, 21)
+xLLM_fidelity = [
+    0.1,
+    0.125,
+    0.15,
+    0.1625,
+    0.175,
+    0.1875,
+    0.2,
+    0.2125,
+    0.225,
+    0.2375,
+    0.25,
+    0.25625,
+    0.2625,
+    0.26875,
+    0.275,
+    0.275,
+    0.275,
+    0.275,
+    0.275,
+    0.275,
+]
+single_steps = [0, 21]
+single_pass_fidelity = [0.1] * len(single_steps)
+
+# Axes Limits and Labels
+xlabel_value = "# of Steps"
+xlim_values = [0, 21]
+xticks_values = [0, 5, 10, 15, 20]
+
+ylabel_value = "Avg. Fidelity"
+ylim_values = [0, 100]
+
+# Labels
+label_1 = "xLLM"
+label_2 = "Single-Pass LLM"
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+# Plotting the lines
+plt.figure(figsize=(4, 3))
+plt.plot(xllm_steps, xLLM_fidelity, "o-.", label=label_1, color="#8280cd")
+plt.plot(single_steps, single_pass_fidelity, "-", label=label_2, color="red")
+
+# Adding legend
+plt.legend()
+
+# Labeling axes
+plt.xlabel(xlabel_value)
+plt.ylabel(ylabel_value)
+plt.xlim(xlim_values)
+plt.xticks(xticks_values)
+
+# ===================
+# Part 4: Saving Output
+# ===================
+# Display the plot with tight layout to minimize white space
+plt.tight_layout()
+plt.savefig('line_29.pdf', bbox_inches='tight')

ChartMimic/dataset/ori_500/line_38.py

@@ -0,0 +1,67 @@
+# ===================
+# Part 1: Importing Libraries
+# ===================
+import matplotlib.pyplot as plt
+import numpy as np; np.random.seed(0)
+
+
+# ===================
+# Part 2: Data Preparation
+# ===================
+# Data
+epochs = ["3", "10", "30", "100"]  # Treat epochs as strings to make them categorical
+gpt_neo = [0.8, 0.8, 0.8, 0.8]
+model_3 = [0.7, 0.65, 0.6, 0.75]
+model_5 = [0.65, 0.75, 0.35, 0.5]
+model_7 = [0.6, 0.65, 0.5, 0.65]
+model_10 = [0.45, 0.5, 0.45, 0.4]
+model_30 = [0.3, 0.45, 0.75, 0.35]
+
+# Axes Limits and Labels
+xlabel_value = "# Epochs"
+
+ylabel_value = "MA"
+ylim_values = [0.0, 0.83]
+yticks_values = np.arange(0.0, 0.81, 0.2)
+
+# Labels
+label_GPT_Neo="GPT-Neo"
+label_3 = "3"
+label_5 = "5"
+label_7 = "7"
+label_10 = "10"
+label_30 = "30"
+
+# ===================
+# Part 3: Plot Configuration and Rendering
+# ===================
+# Plot
+plt.figure(figsize=(6, 3))
+plt.axhline(y=0.8, color="black", linestyle="--", linewidth=1, label=label_GPT_Neo)
+plt.plot(epochs, model_3, "r-", marker="s", label=label_3)
+plt.plot(epochs, model_5, "y-", marker="s", label=label_5)
+plt.plot(epochs, model_7, "k-", marker="s", label=label_7)
+plt.plot(epochs, model_10, "b-", marker="s", label=label_10)
+plt.plot(epochs, model_30, "g-", marker="s", label=label_30)
+
+plt.yticks(yticks_values, fontsize=14)
+plt.ylim(ylim_values)
+
+# Set x-axis labels equidistantly
+ax = plt.gca()
+ax.set_xticks(np.arange(len(epochs)))  # Positional indexing for equidistant spacing
+ax.set_xticklabels(epochs, fontsize=14)  # Labeling x-ticks as per epochs
+
+plt.xlabel(xlabel_value, fontsize=16)
+plt.ylabel(ylabel_value, fontsize=16)
+
+plt.legend(
+    loc="lower left", ncol=3, fontsize=12, columnspacing=5
+)  # Adjusted legend settings
+
+# ===================
+# Part 4: Saving Output
+# ===================
+# Adjust layout and show plot
+plt.tight_layout()
+plt.savefig('line_38.pdf', bbox_inches='tight')