How to Make a Scatter Plot in Python With plt.scatter()

visualizing-python-plt-scatter/README.md

@@ -0,0 +1,3 @@
+# How to Make a Scatter Plot in Python With plt.scatter()
+
+This folder provides the code examples for the Real Python tutorial [How to Make a Scatter Plot in Python With plt.scatter()](https://realpython.com/visualizing-python-plt-scatter/)

visualizing-python-plt-scatter/requirements.txt

@@ -0,0 +1,2 @@
+matplotlib==3.10.1
+numpy==2.2.4

visualizing-python-plt-scatter/step_01_basic_scatter.py

@@ -0,0 +1,10 @@
+# Sections: Getting Started With plt.scatter() / Comparing plt.scatter() and plt.plot()
+
+import matplotlib.pyplot as plt
+
+price = [2.50, 1.23, 4.02, 3.25, 5.00, 4.40]
+sales_per_day = [34, 62, 49, 22, 13, 19]
+
+plt.scatter(price, sales_per_day)
+# plt.plot(price, sales_per_day, "o")  # equivalent using plt.plot()
+plt.show()

visualizing-python-plt-scatter/step_02_timing_comparison.py

@@ -0,0 +1,24 @@
+# Section: Comparing plt.scatter() and plt.plot()
+
+import timeit
+import matplotlib.pyplot as plt  # noqa: F401
+
+price = [2.50, 1.23, 4.02, 3.25, 5.00, 4.40]
+sales_per_day = [34, 62, 49, 22, 13, 19]
+
+print(
+    "plt.scatter()",
+    timeit.timeit(
+        "plt.scatter(price, sales_per_day)",
+        number=1000,
+        globals=globals(),
+    ),
+)
+print(
+    "plt.plot()",
+    timeit.timeit(
+        "plt.plot(price, sales_per_day, 'o')",
+        number=1000,
+        globals=globals(),
+    ),
+)

visualizing-python-plt-scatter/step_03_size_encoding.py

@@ -0,0 +1,11 @@
+# Section: Changing the Size
+
+import matplotlib.pyplot as plt
+import numpy as np
+
+price = np.asarray([2.50, 1.23, 4.02, 3.25, 5.00, 4.40])
+sales_per_day = np.asarray([34, 62, 49, 22, 13, 19])
+profit_margin = np.asarray([20, 35, 40, 20, 27.5, 15])
+
+plt.scatter(x=price, y=sales_per_day, s=profit_margin * 10)
+plt.show()

visualizing-python-plt-scatter/step_04_size_and_color.py

@@ -0,0 +1,22 @@
+# Section: Changing the Color
+
+import matplotlib.pyplot as plt
+import numpy as np
+
+price = np.asarray([2.50, 1.23, 4.02, 3.25, 5.00, 4.40])
+sales_per_day = np.asarray([34, 62, 49, 22, 13, 19])
+profit_margin = np.asarray([20, 35, 40, 20, 27.5, 15])
+
+low = (0, 1, 0)
+medium = (1, 1, 0)
+high = (1, 0, 0)
+
+sugar_content = [low, high, medium, medium, high, low]
+
+plt.scatter(
+    x=price,
+    y=sales_per_day,
+    s=profit_margin * 10,
+    c=sugar_content,
+)
+plt.show()

visualizing-python-plt-scatter/step_05_two_products.py

@@ -0,0 +1,32 @@
+# Section: Changing the Shape
+
+import matplotlib.pyplot as plt
+import numpy as np
+
+low = (0, 1, 0)
+medium = (1, 1, 0)
+high = (1, 0, 0)
+
+price_orange = np.asarray([2.50, 1.23, 4.02, 3.25, 5.00, 4.40])
+sales_per_day_orange = np.asarray([34, 62, 49, 22, 13, 19])
+profit_margin_orange = np.asarray([20, 35, 40, 20, 27.5, 15])
+sugar_content_orange = [low, high, medium, medium, high, low]
+
+price_cereal = np.asarray([1.50, 2.50, 1.15, 1.95])
+sales_per_day_cereal = np.asarray([67, 34, 36, 12])
+profit_margin_cereal = np.asarray([20, 42.5, 33.3, 18])
+sugar_content_cereal = [low, high, medium, low]
+
+plt.scatter(
+    x=price_orange,
+    y=sales_per_day_orange,
+    s=profit_margin_orange * 10,
+    c=sugar_content_orange,
+)
+plt.scatter(
+    x=price_cereal,
+    y=sales_per_day_cereal,
+    s=profit_margin_cereal * 10,
+    c=sugar_content_cereal,
+)
+plt.show()

visualizing-python-plt-scatter/step_06_two_products_markers.py

@@ -0,0 +1,33 @@
+# Section: Changing the Shape
+
+import matplotlib.pyplot as plt
+import numpy as np
+
+low = (0, 1, 0)
+medium = (1, 1, 0)
+high = (1, 0, 0)
+
+price_orange = np.asarray([2.50, 1.23, 4.02, 3.25, 5.00, 4.40])
+sales_per_day_orange = np.asarray([34, 62, 49, 22, 13, 19])
+profit_margin_orange = np.asarray([20, 35, 40, 20, 27.5, 15])
+sugar_content_orange = [low, high, medium, medium, high, low]
+
+price_cereal = np.asarray([1.50, 2.50, 1.15, 1.95])
+sales_per_day_cereal = np.asarray([67, 34, 36, 12])
+profit_margin_cereal = np.asarray([20, 42.5, 33.3, 18])
+sugar_content_cereal = [low, high, medium, low]
+
+plt.scatter(
+    x=price_orange,
+    y=sales_per_day_orange,
+    s=profit_margin_orange * 10,
+    c=sugar_content_orange,
+)
+plt.scatter(
+    x=price_cereal,
+    y=sales_per_day_cereal,
+    s=profit_margin_cereal * 10,
+    c=sugar_content_cereal,
+    marker="d",
+)
+plt.show()

visualizing-python-plt-scatter/step_07_two_products_labels_alpha.py

@@ -0,0 +1,46 @@
+# Section: Changing the Transparency
+
+import matplotlib.pyplot as plt
+import numpy as np
+
+low = (0, 1, 0)
+medium = (1, 1, 0)
+high = (1, 0, 0)
+
+price_orange = np.asarray([2.50, 1.23, 4.02, 3.25, 5.00, 4.40])
+sales_per_day_orange = np.asarray([34, 62, 49, 22, 13, 19])
+profit_margin_orange = np.asarray([20, 35, 40, 20, 27.5, 15])
+sugar_content_orange = [low, high, medium, medium, high, low]
+
+price_cereal = np.asarray([1.50, 2.50, 1.15, 1.95])
+sales_per_day_cereal = np.asarray([67, 34, 36, 12])
+profit_margin_cereal = np.asarray([20, 42.5, 33.3, 18])
+sugar_content_cereal = [low, high, medium, low]
+
+plt.scatter(
+    x=price_orange,
+    y=sales_per_day_orange,
+    s=profit_margin_orange * 10,
+    c=sugar_content_orange,
+    alpha=0.5,
+)
+plt.scatter(
+    x=price_cereal,
+    y=sales_per_day_cereal,
+    s=profit_margin_cereal * 10,
+    c=sugar_content_cereal,
+    marker="d",
+    alpha=0.5,
+)
+
+plt.title("Sales vs Prices for Orange Drinks and Cereal Bars")
+plt.legend(["Orange Drinks", "Cereal Bars"])
+plt.xlabel("Price (Currency Unit)")
+plt.ylabel("Average weekly sales")
+plt.text(
+    3.2,
+    55,
+    "Size of marker = profit margin\nColor of marker = sugar content",
+)
+
+plt.show()

visualizing-python-plt-scatter/step_08_colormap.py

@@ -0,0 +1,45 @@
+# Section: Customizing the Colormap and Style of Your Scatter Plot
+
+import matplotlib.pyplot as plt
+import numpy as np
+
+price_orange = np.asarray([2.50, 1.23, 4.02, 3.25, 5.00, 4.40])
+sales_per_day_orange = np.asarray([34, 62, 49, 22, 13, 19])
+profit_margin_orange = np.asarray([20, 35, 40, 20, 27.5, 15])
+sugar_content_orange = [15, 35, 22, 27, 38, 14]
+
+price_cereal = np.asarray([1.50, 2.50, 1.15, 1.95])
+sales_per_day_cereal = np.asarray([67, 34, 36, 12])
+profit_margin_cereal = np.asarray([20, 42.5, 33.3, 18])
+sugar_content_cereal = [21, 49, 29, 24]
+
+plt.scatter(
+    x=price_orange,
+    y=sales_per_day_orange,
+    s=profit_margin_orange * 10,
+    c=sugar_content_orange,
+    cmap="jet",
+    alpha=0.5,
+)
+plt.scatter(
+    x=price_cereal,
+    y=sales_per_day_cereal,
+    s=profit_margin_cereal * 10,
+    c=sugar_content_cereal,
+    cmap="jet",
+    marker="d",
+    alpha=0.5,
+)
+
+plt.title("Sales vs Prices for Orange Drinks and Cereal Bars")
+plt.legend(["Orange Drinks", "Cereal Bars"])
+plt.xlabel("Price (Currency Unit)")
+plt.ylabel("Average weekly sales")
+plt.text(
+    2.7,
+    55,
+    "Size of marker = profit margin\nColor of marker = sugar content",
+)
+plt.colorbar()
+
+plt.show()

visualizing-python-plt-scatter/step_09_bus_distribution.py

@@ -0,0 +1,18 @@
+# Section: Further Scatter Plot Techniques With plt.scatter()
+
+import matplotlib.pyplot as plt
+import numpy as np
+
+mean = 15, 45
+sd = 5, 7
+
+x = np.linspace(0, 59, 60)  # Represents each minute within the hour
+first_distribution = np.exp(-0.5 * ((x - mean[0]) / sd[0]) ** 2)
+second_distribution = 0.9 * np.exp(-0.5 * ((x - mean[1]) / sd[1]) ** 2)
+y = first_distribution + second_distribution
+y = y / max(y)
+
+plt.plot(x, y)
+plt.ylabel("Relative probability of bus arrivals")
+plt.xlabel("Minutes past the hour")
+plt.show()

visualizing-python-plt-scatter/step_10_bus_random_scatter.py

@@ -0,0 +1,15 @@
+# Section: Further Scatter Plot Techniques With plt.scatter()
+
+import random
+import matplotlib.pyplot as plt
+import numpy as np
+
+n_buses = 40
+bus_times = np.asarray([random.randint(0, 59) for _ in range(n_buses)])
+bus_likelihood = np.asarray([random.random() for _ in range(n_buses)])
+
+plt.scatter(x=bus_times, y=bus_likelihood)
+plt.title("Randomly chosen bus arrival times and relative probabilities")
+plt.ylabel("Relative probability of bus arrivals")
+plt.xlabel("Minutes past the hour")
+plt.show()

visualizing-python-plt-scatter/step_11_bus_combined.py

@@ -0,0 +1,25 @@
+# Section: Further Scatter Plot Techniques With plt.scatter()
+
+import random
+import matplotlib.pyplot as plt
+import numpy as np
+
+mean = 15, 45
+sd = 5, 7
+
+x = np.linspace(0, 59, 60)
+first_distribution = np.exp(-0.5 * ((x - mean[0]) / sd[0]) ** 2)
+second_distribution = 0.9 * np.exp(-0.5 * ((x - mean[1]) / sd[1]) ** 2)
+y = first_distribution + second_distribution
+y = y / max(y)
+
+n_buses = 40
+bus_times = np.asarray([random.randint(0, 59) for _ in range(n_buses)])
+bus_likelihood = np.asarray([random.random() for _ in range(n_buses)])
+
+plt.scatter(x=bus_times, y=bus_likelihood)
+plt.plot(x, y)
+plt.title("Randomly chosen bus arrival times and relative probabilities")
+plt.ylabel("Relative probability of bus arrivals")
+plt.xlabel("Minutes past the hour")
+plt.show()

visualizing-python-plt-scatter/step_12_bus_in_out_region.py

@@ -0,0 +1,39 @@
+# Section: Further Scatter Plot Techniques With plt.scatter()
+
+import random
+import matplotlib.pyplot as plt
+import numpy as np
+
+mean = 15, 45
+sd = 5, 7
+
+x = np.linspace(0, 59, 60)
+first_distribution = np.exp(-0.5 * ((x - mean[0]) / sd[0]) ** 2)
+second_distribution = 0.9 * np.exp(-0.5 * ((x - mean[1]) / sd[1]) ** 2)
+y = first_distribution + second_distribution
+y = y / max(y)
+
+n_buses = 40
+bus_times = np.asarray([random.randint(0, 59) for _ in range(n_buses)])
+bus_likelihood = np.asarray([random.random() for _ in range(n_buses)])
+
+in_region = bus_likelihood < y[bus_times]
+out_region = bus_likelihood >= y[bus_times]
+
+plt.scatter(
+    x=bus_times[in_region],
+    y=bus_likelihood[in_region],
+    color="green",
+)
+plt.scatter(
+    x=bus_times[out_region],
+    y=bus_likelihood[out_region],
+    color="red",
+    marker="x",
+)
+
+plt.plot(x, y)
+plt.title("Randomly chosen bus arrival times and relative probabilities")
+plt.ylabel("Relative probability of bus arrivals")
+plt.xlabel("Minutes past the hour")
+plt.show()