[USER (data scientist)]: Lastly, can you whip up a bar chart showing the number of matches played on different surface types? Please generate the code with the output in plot type.
My template of code snippet is:

---BEGIN CODE TEMPLATE---

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from decision_company import read_csv_file, count_unique_values, transform, generate_summary_stat, concatenate_objects, create_dataframe, generate_summary_stat, create_subplots, create_histogram, create_histogram_subplot, set_plot_split_title, show_plots, make_xlabel, save_plot, create_scatter_plot, make_ylabel, create_bar_chart, show_plots

atp_tennis = read_csv_file('atp_tennis.csv')

fig3, ax3 = create_subplots()

# YOUR SOLUTION BEGIN:
<code1>
[GENERATE YOUR CODE] 
</code1>
# YOUR SOLUTION END

# save data
save_plot('./pred_result/bar_chart.png')
show_plots()

---END CODE TEMPLATE---

[YOU (AI assistant)]: Of course! Here's the code to create a bar chart using pandas and matplotlib: 

# MY SOLUTION BEGIN:
