Added bar plots

GeorgeSeif · GeorgeSeif · commit 174fea1a7707 · 2017-08-22T18:54:57.000-04:00
diff --git a/README.md b/README.md
@@ -38,6 +38,7 @@ To install all of the libraries, run the commands in the "install.txt" file. The
 - **Scatterplot:** A scatter plot is a graphical method of displaying the relationship between data points. Each feature variable is assigned an axis. Each data point in the dataset is then plotted based on its feature values.
 - **Beeswarm Plot:** A Beeswarm plot is a two-dimensional visualisation technique where data points are plotted relative to a fixed reference axis so that no two datapoints overlap. The beeswarm plot is a useful technique when we wish to see not only the measured values of interest for each data point, but also the distribution of these values. 
 - **Cumulative Distribution Function:** The cumulative distribution function (cdf) is the probability that a variable takes a value less than or equal to x. For example, we may wish to see what percentage of the data has a certain feature variable that is less than or equal to x.
+- **Bar Plots:** Classical bar plots that are good for visualisation and comparison of different data statistics, especially comparing statistics of feature variables.
 
 #### Statistics
 - **Mean and Median:** Both of these show a type of "average" or "center" value for a particular feature variable. The mean is the more literal and precise center; however median is much more robust to outliers which may pull the mean value calculation far away from the majority of the values. 
diff --git a/explore_wine_data.py b/explore_wine_data.py
@@ -5,6 +5,9 @@
 import matplotlib.pyplot as plt
 from sklearn.datasets import load_wine
 
+
+# ------------------------------------------------------------------------------------------------
+
 # Read in the data
 # NOTE that this loads as a dictionairy
 wine_data = load_wine()
@@ -19,15 +22,21 @@
 
 print("The wine dataset has " + str(num_features) + " features")
 print(wine_data.feature_names)
-print("The wine dataset has " + str(num_classes) + " classes")
+print("The wine dataset has " + str(num_classes) + " categoryes")
 print(wine_data.target_names)
 
 
 # Put everything into a Pandas DataFrame
-data = pd.DataFrame(data=np.c_[train_data, train_labels], columns=wine_data.feature_names + ['class'])
+data = pd.DataFrame(data=np.c_[train_data, train_labels], columns=wine_data.feature_names + ['category'])
 # print(tabulate(data, headers='keys', tablefmt='psql'))
 
+# ------------------------------------------------------------------------------------------------
+
+
+
+
 
+# ------------------------------------------------------------------------------------------------
 
 # Create histogram
 hist_feature_name='color_intensity'
@@ -38,7 +47,72 @@
 plt.xlabel(hist_feature_name)
 plt.show()
 
+# ------------------------------------------------------------------------------------------------
+
+
+
+
+
+
+
+# ------------------------------------------------------------------------------------------------
+
+# Create grouped bar plot
+
+
+var_name_1 = 'alcohol'
+var_name_2 = 'color_intensity'
+
+
+# Setting the positions and width for the bars
+pos = list(range(num_classes))
+width = 0.1
+
+# Plotting the bars
+fig, ax = plt.subplots(figsize=(10,5))
+
+# Set the position of the x ticks
+ax.set_xticks([p + 1.5 * width for p in pos])
+ax.set_xticklabels(list(range(num_classes)))
+
+class_0_data = data[data.category==0]
+alcohol_values_0 = class_0_data[var_name_1].values 
+mean_alcohol_0 = np.mean(alcohol_values_0)
+color_values_0 = class_0_data[var_name_2].values 
+mean_color_0 = np.mean(color_values_0)
+
+class_1_data = data[data.category==1]
+alcohol_values_1 = class_1_data[var_name_1].values 
+mean_alcohol_1 = np.mean(alcohol_values_1)
+color_values_1 = class_1_data[var_name_2].values 
+mean_color_1 = np.mean(color_values_1)
 
+class_2_data = data[data.category==2]
+alcohol_values_2 = class_2_data[var_name_1].values 
+mean_alcohol_2 = np.mean(alcohol_values_2)
+color_values_2 = class_2_data[var_name_2].values 
+mean_color_2 = np.mean(color_values_2)
+
+plt.bar(pos, [mean_alcohol_0, mean_alcohol_1, mean_alcohol_2], width, alpha=1.0, color='#EE3224', label='alcohol')
+plt.bar([p + width for p in pos], [mean_color_0, mean_color_1, mean_color_2], width, alpha=1.0, color='#F78F1E', label='color_intensity')
+
+
+plt.legend([var_name_1, 'color_intensity'], loc='upper left')
+
+plt.show()
+
+
+# ------------------------------------------------------------------------------------------------
+
+
+
+
+
+
+
+
+
+# ------------------------------------------------------------------------------------------------
 
 # Create scatterplot
 scatter_feature_name_1='color_intensity'
@@ -52,18 +126,27 @@
 
 
 # Create scatterplot matrix
-fig = sns.pairplot(data=data[['alcohol', 'color_intensity', 'malic_acid', 'magnesium', 'class']], hue='class')
+fig = sns.pairplot(data=data[['alcohol', 'color_intensity', 'malic_acid', 'magnesium', 'category']], hue='category')
 
 plt.show()
 
+# ------------------------------------------------------------------------------------------------
 
 
+
+# ------------------------------------------------------------------------------------------------
+
 # Create bee swarm plot
-sns.swarmplot(x='class', y='total_phenols', data=data)
+sns.swarmplot(x='category', y='total_phenols', data=data)
 plt.show()
 
+# ------------------------------------------------------------------------------------------------
+
+
+
 
 
+# ------------------------------------------------------------------------------------------------
 
 # Cumulative Distribution Function Plots
 
