def silhouettes(name, X_train, max_clusters = 15, min_clusters = 5, save = False):
'''
'''
X_train = X_train.copy()
num_numerical = ds.get_number_numerical(name)
X_train_s_numerical = split.standardize(name, X_train).iloc[:,0:num_numerical]
cluster_range = range(min_clusters,max_clusters+1)
for clusters in cluster_range:
fig, ax = plt.subplots()
fig.set_size_inches(18, 7)
# The 1st subplot is the silhouette plot
# The silhouette coefficient can range from -1, 1 but in this example all
# lie within [-0.1, 1]
ax.set_xlim([-0.7, 1])
# The (n_clusters+1)*10 is for inserting blank space between silhouette
# plots of individual clusters, to demarcate them clearly.
ax.set_ylim([0, len(X_train_s_numerical) + (clusters + 1) * 10])
cluster_labels = kmeans(name, clusters, X_train_s_numerical).predict(X_train_s_numerical)
silhouette_avg = silhouette_score(X_train_s_numerical, cluster_labels)
print("For n_clusters =", clusters, "The average silhouette_score is :", silhouette_avg)
cluster_silhouette = silhouette_samples(X_train_s_numerical, cluster_labels)
y_lower = 10
for i in range(clusters):
ith_cluster_silhouette_values = cluster_silhouette[cluster_labels == i]
ith_cluster_silhouette_values.sort()
size_cluster_i = ith_cluster_silhouette_values.shape[0]
y_upper = y_lower + size_cluster_i
color = cm.nipy_spectral(float(i) / clusters)
ax.fill_betweenx(np.arange(y_lower, y_upper), 0, ith_cluster_silhouette_values,
facecolor=color, edgecolor=color, alpha=0.7)
# Label the silhouette plots with their cluster numbers at the middle
ax.text(-0.05, y_lower + 0.5 * size_cluster_i, str(i))
# Compute the new y_lower for next plot
y_lower = y_upper + 10 # 10 for the 0 samples
ax.set_title("The silhouette plot for the various clusters.")
ax.set_xlabel("The silhouette coefficient values")
ax.set_ylabel("Cluster label")
# The vertical line for average silhouette score of all the values
ax.axvline(x=silhouette_avg, color="red", linestyle="--")
ax.set_yticks([]) # Clear the yaxis labels / ticks
ax.set_xticks(np.arange(-0.6,1.1,0.2))
plt.show()
if save:
to_save = Path().resolve().joinpath('data', 'visualizations', '{}_elbow.png'.format(name))
fig.savefig(to_save)
def find_vifs(name, X_train, tolerance=5):
'''Iteratively drops features from set of numerical training features based off of VIF scores.
'''
X_train = X_train.copy()
number_numerical = ds.get_number_numerical()[name]
train_num = X_train.iloc[:, 0:number_numerical]
vif = pd.DataFrame(index=train_num.columns)
vif_x = train_num.copy()
cols = vif_x.columns.values
for i in np.arange(len(train_num.columns)):
try:
vifs = [
variance_inflation_factor(vif_x.values, i)
for i in range(vif_x.shape[1])
]
vifs_df = pd.DataFrame(vifs,
columns=["VIF Round {}".format(i)],
index=cols)
if max(vifs) > tolerance:
loc = np.where(vifs == max(vifs))[0][0]
vif_x = vif_x.drop([cols[loc]], axis=1)
cols = np.delete(cols, loc, axis=0)
else:
vif = pd.concat([vif, vifs_df], axis=1)
break
vif = pd.concat([vif, vifs_df], axis=1)
except:
break
return vif
def pca(name, X_train, X_test, dimension):
"""
"""
X_train = X_train.copy()
X_test = X_test.copy()
num_numerical = ds.get_number_numerical(name)
X_train_s = split.standardize(name, X_train)
X_test_s = split.standardize(name, X_test)
X_train_s_numerical = X_train_s.iloc[:, 0:num_numerical]
X_train_s_categorical = X_train_s.iloc[:, num_numerical:]
X_test_s_numerical = X_test_s.iloc[:, 0:num_numerical]
X_test_s_categorical = X_test_s.iloc[:, num_numerical:]
estimator = PCA(dimension)
X_train_s_numerical_reduced = pd.DataFrame(
estimator.fit_transform(X_train_s_numerical),
index=X_train_s_categorical.index)
X_test_s_numerical_reduced = pd.DataFrame(
estimator.transform(X_test_s_numerical),
index=X_test_s_categorical.index)
X_train_s = pd.concat([X_train_s_numerical_reduced, X_train_s_categorical],
axis=1)
X_test_s = pd.concat([X_test_s_numerical_reduced, X_test_s_categorical],
axis=1)
return X_train_s, X_test_s
def elbow_method_kmeans(name, max_clusters = 30, min_clusters = 2, save = False):
'''Creates elbow method plot for varying number of clusters.
Y-axis is the sum of squared distances of samples to their closest cluster center.
'''
display_name = ds.get_names()[name]
X_train, X_test= split.split_subset(name)[0:1]
num_numerical = ds.get_number_numerical()[name]
X_train_numerical = X_train.iloc[:,0:num_numerical]
distortions = []
cluster_range = range(min_clusters,max_clusters)
for clusters in cluster_range:
kmean = kmeans(name, clusters, X_train_numerical)
distortions.append(kmean.inertia_)
fig, ax = plt.subplots(figsize=(10, 10))
ax.plot(cluster_range, distortions, marker = 'o')
ax.set_title('Elbow Method for KMeans for {}'.format(display_name), size=25)
ax.set_xlabel('Number of Clusters', fontsize = 20)
ax.set_ylabel('Sum of Squared Distances', fontsize = 20)
plt.show()
if save:
to_save = Path().resolve().joinpath('visualizations', 'clustering_elbow_{}.png'.format(name))
fig.savefig(to_save, dpi=300)
def main_datasets():
'''
'''
pd.set_option('display.max_rows', 2)
number_numerical = ds.get_number_numerical()
dsets = ds.load_datasets(names = ['dataset_1', 'dataset_2', 'dataset_3'])
display(Markdown('### `Dataset 1:` {} features: {} numerical, {} categorical, 1 response'.format(\
len(dsets['dataset_1'].columns)-1,
number_numerical['dataset_1'],
len(dsets['dataset_1'].columns)\
-1-number_numerical['dataset_1'])))
display(dsets['dataset_1'])
display(Markdown('---'))
display(Markdown('### `Dataset 2:` {} features: {} numerical, {} categorical, 1 response'.format(\
len(dsets['dataset_2'].columns)-1,
number_numerical['dataset_2'],
len(dsets['dataset_2'].columns)\
-1-number_numerical['dataset_2'])))
display(dsets['dataset_2'])
display(Markdown('---'))
display(Markdown('### `Dataset 3:` {} features: {} numerical, {} categorical, 1 response'.format(\
len(dsets['dataset_3'].columns)-1,
number_numerical['dataset_3'],
len(dsets['dataset_3'].columns)\
-1-number_numerical['dataset_3'])))
display(dsets['dataset_3'])
display(Markdown('---'))
def main_datasets_split():
'''
'''
number_numerical = ds.get_number_numerical()
pd.set_option('display.max_rows', 2)
dsets = split.split_subsets(['dataset_1', 'dataset_2', 'dataset_3'])
display(Markdown('### `Dataset 1 Training Set:` {} features: {} numerical, {} categorical, 1 response'.format(\
len(dsets['dataset_1'][4].columns),
number_numerical['dataset_1'],
len(dsets['dataset_1'][4].columns)\
-number_numerical['dataset_1'])))
display(dsets['dataset_1'][4])
display(Markdown('---'))
display(Markdown('### `Dataset 2 Training Set:` {} features: {} numerical, {} categorical, 1 response'.format(\
len(dsets['dataset_2'][4].columns),
number_numerical['dataset_2'],
len(dsets['dataset_2'][4].columns)\
-number_numerical['dataset_2'])))
display(dsets['dataset_2'][4])
display(Markdown('---'))
display(Markdown('### `Dataset 3 Training Set:` {} features: {} numerical, {} categorical, 1 response'.format(\
len(dsets['dataset_3'][4].columns),
number_numerical['dataset_3'],
len(dsets['dataset_3'][4].columns)\
-number_numerical['dataset_3'])))
display(dsets['dataset_3'][4])
display(Markdown('---'))
def kmeans(name, n_clusters, X_train, X_test): ''' ''' X_train = X_train.copy() X_test = X_test.copy() num_numerical = ds.get_number_numerical()[name] X_train_s_numerical = split.standardize(name, X_train, X_test)[0].iloc[:,0:num_numerical] return KMeans(n_clusters= n_clusters, random_state=18, n_jobs = -1).fit(X_train_s_numerical)
def create_heatmap(name, train, save=False):
'''Creates and/or saves a heatmap of the correlation between the numerical variables of a train.
'''
train = train.copy()
num_numerical = ds.get_number_numerical(name)
train_num = train.iloc[:, 0:num_numerical]
fig, ax = plt.subplots(figsize=(15, 15))
heat = sns.heatmap(train_num.corr(),
annot=True,
ax=ax,
fmt='.2f',
cbar=True,
square=True,
xticklabels=True,
yticklabels=True,
annot_kws={'size': 16},
cmap='coolwarm',
center=0,
vmin=-1,
vmax=1,
cbar_kws={"shrink": .82})
ax.set_title(
'Heatmap of Numerical Variable Correlation for {}'.format(name),
size=25)
plt.yticks(rotation=0, size=15)
plt.xticks(rotation=30, size=15)
ax.collections[0].colorbar.ax.tick_params(labelsize=15)
# Make annotations larger if abs(correlation) above 0.2
num_corrs = len(np.unique(train_num.corr().values.flatten()))
bigs = []
for i in np.arange(2, num_corrs + 1):
val = round(
np.sort(np.abs(np.unique(train_num.corr().values.flatten())))[-i],
2)
if val > 0.2:
bigs = np.append(bigs, val)
for text in heat.texts:
num = pd.to_numeric(text.get_text())
i = np.where(bigs == abs(num))[0]
if i.size > 0:
text.set_color('white')
text.set_size(40 - (i[0] * 3))
plt.show()
if save:
to_save = Path().resolve().joinpath('data', 'visualizations',
'{}_heatmap.png'.format(name))
fig.savefig(to_save)
def pca_cv(name, save=False):
'''
'''
display_name = ds.get_names()[name]
X_train, X_test, y_train, y_test, train = split.split_subset(name)
num_numerical = ds.get_number_numerical()[name]
X_train_s, X_test_s = split.standardize(name, X_train, X_test)
X_train_s_numerical = X_train_s.iloc[:, 0:num_numerical]
X_train_s_categorical = X_train_s.iloc[:, num_numerical:]
X_test_s_numerical = X_test_s.iloc[:, 0:num_numerical]
X_test_s_categorical = X_test_s.iloc[:, num_numerical:]
df = pd.DataFrame()
ols = LinearRegression()
ev = []
for i in np.arange(1, num_numerical):
pca = PCA(i, random_state=18)
X_train_s_numerical_reduced = pd.DataFrame(
pca.fit_transform(X_train_s_numerical),
index=X_train_s_categorical.index)
X_test_s_numerical_reduced = pd.DataFrame(
pca.transform(X_test_s_numerical),
index=X_test_s_categorical.index)
X_train_s = pd.concat(
[X_train_s_numerical_reduced, X_train_s_categorical], axis=1)
X_test_s = pd.concat(
[X_test_s_numerical_reduced, X_test_s_categorical], axis=1)
model = ols.fit(X_train_s, y_train)
preds = model.predict(X_test_s)
preds = metrics.apply_metrics(
'{}: {} dimensions'.format(display_name, i), y_test, preds.ravel(),
y_train)
df = pd.concat([df, preds], axis=0)
ev.append(1 - sum(pca.explained_variance_))
if save:
to_save = Path().resolve().joinpath('features', 'pca',
'{}.csv'.format(name))
df.to_csv(to_save)
return df, ev
def find_numerical_significance(name, X_train, y_train):
'''Returns P-value of hypothesis test where H0 is that the feature has no effect on the outcome and
an estimate of the mutual information
'''
X_train = X_train.copy()
y_train = y_train.copy()
number_numerical = ds.get_number_numerical()
train_num = X_train.iloc[:, 0:number_numerical[name]]
f_r = pd.DataFrame(f_regression(train_num, y_train)[1],
index=train_num.columns.values,
columns=["F-test (P-Value)"])
mir = pd.DataFrame(mutual_info_regression(train_num,
y_train,
random_state=18),
index=train_num.columns.values,
columns=["Estimated Mutual Information"])
df = pd.concat([f_r, mir], axis=1)
return df
def create_cluster_plots(name, save = False):
'''
'''
X_train,X_test = split.split_subset(name)[0:2]
num_numerical = ds.get_number_numerical()[name]
X_train_numerical = X_train.iloc[:,0:num_numerical]
X_test_numerical = X_test.iloc[:,0:num_numerical]
distortions = []
cluster_range = range(2,31)
for clusters in cluster_range:
kmean = kmeans(name, clusters, X_train, X_test)
distortions.append(kmean.inertia_)
fig, ax = plt.subplots(ncols = 2, figsize=(40, 12))
ax[0].plot(cluster_range, distortions, marker = 'o')
ax[0].set_title('KMeans Scree Plot', fontsize = 40)
ax[0].set_xlabel('Number of Clusters', fontsize = 30)
ax[0].set_ylabel('Sum of Squared Distances', fontsize = 30)
ax[0].tick_params(labelsize=20)
for i, txt in enumerate(cluster_range):
annot = ax[0].annotate('{}'.format(txt), (cluster_range[i],distortions[i]))
annot.set_fontsize(25)
X_train_s_numerical = split.standardize(name, X_train_numerical, X_test_numerical)[0]
clusters = 7
if name == 'dataset_3':
clusters = 9
ax[1].set_xlim([-0.3, 0.8])
ax[1].set_ylim([0, len(X_train_s_numerical) + (clusters + 1) * 10])
cluster_labels = kmeans(name, clusters, X_train, X_test).predict(X_train_s_numerical)
silhouette_avg = silhouette_score(X_train_s_numerical, cluster_labels)
cluster_silhouette = silhouette_samples(X_train_s_numerical, cluster_labels)
y_lower = 10
for i in range(clusters):
ith_cluster_silhouette_values = cluster_silhouette[cluster_labels == i]
ith_cluster_silhouette_values.sort()
size_cluster_i = ith_cluster_silhouette_values.shape[0]
y_upper = y_lower + size_cluster_i
color = cm.nipy_spectral(float(i) / clusters)
ax[1].fill_betweenx(np.arange(y_lower, y_upper), 0, ith_cluster_silhouette_values,
facecolor=color, edgecolor=color, alpha=0.7)
ax[1].text(-0.05, y_lower + 0.5 * size_cluster_i, str(i), fontsize = 25)
y_lower = y_upper + 10
ax[1].set_title("Silhouette plot for {} clusters.".format(clusters) , fontsize = 40)
ax[1].set_xlabel("Silhouette Coefficient Values",fontsize = 30)
ax[1].set_ylabel("Cluster label",fontsize = 30)
ax[1].axvline(x=silhouette_avg, color="red", linestyle="--")
ax[1].set_yticks([])
ax[1].set_xticks(np.arange(-0.3,0.9,0.1))
ax[1].tick_params(labelsize=20)
plt.tight_layout()
plt.show()
if save:
to_save = Path().resolve().joinpath('visualizations', 'clustering', '{}.png'.format(name))
fig.savefig(to_save, dpi = 300)
def create_plots(name, save=False):
'''
'''
dset = ds.load_dataset(name)
train = dset
sns.set_style("whitegrid")
sns.set_palette(sns.color_palette('bright', 12))
fig = plt.figure(figsize=(40, 27))
gs = gridspec.GridSpec(4, 4)
ax00 = plt.subplot(gs[0, 0])
ax01 = plt.subplot(gs[0, 1])
ax02 = plt.subplot(gs[0, 2])
ax03 = plt.subplot(gs[0, 3])
ax10 = plt.subplot(gs[1, 0])
ax11 = plt.subplot(gs[1, 1])
ax12 = plt.subplot(gs[1, 2])
ax13 = plt.subplot(gs[1, 3])
ax20 = plt.subplot(gs[2, 0])
ax21 = plt.subplot(gs[2, 1])
ax22 = plt.subplot(gs[2, 2])
ax23 = plt.subplot(gs[2, 3])
ax30 = plt.subplot(gs[3, 0:2])
ax31 = plt.subplot(gs[3, 2:4])
bins = np.arange(4000, 26001, 500)
# fig, ax = plt.subplots(nrows = 4, ncols = 4, figsize=(40, 20))
sns.distplot(train['Attendance'],
ax=ax00,
kde=False,
norm_hist=True,
bins=bins)
ax00.set_xlabel('Attendance (# of people)', fontsize=20)
ax00.set_ylabel('Percent per person', fontsize=20)
ax00.tick_params(labelsize=15)
ax00.set_title(label="Overall Attendance", fontsize=25)
days = train['Day of Week'].unique()
for day in days:
sns.distplot(train.loc[train['Day of Week'] == day]['Attendance'],
ax=ax01,
kde=False,
norm_hist=True,
bins=bins)
ax01.set_title(label="Attendance per Day", fontsize=25)
ax01.set_xlabel('Attendance (# of people)', fontsize=20)
ax01.set_ylabel('Percent per person', fontsize=20)
ax01.tick_params(labelsize=15)
ax01.legend(days, loc="upper right", fontsize=15)
grouped = train[['Day of Week',
'Attendance']].groupby('Day of Week').mean()
order = [
'Monday', "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday",
"Sunday"
]
sns.barplot(x='Attendance',
y=grouped.index,
data=grouped,
order=order,
ci=None,
orient='h',
saturation=1,
ax=ax20,
palette=sns.color_palette("cubehelix", 7))
ax20.set_xlim(16500, 19000)
ax20.set_xticks(range(16500, 19001, 500))
ax20.set_xlabel('Average Attendance (# of people)', fontsize=20)
ax20.set_ylabel('Day of the Week', fontsize=20)
ax20.tick_params(labelsize=15)
ax20.set_title(label="Average Attendance per Day", fontsize=25)
months = train['Month'].unique()
for month in months:
sns.distplot(train.loc[train['Month'] == month]['Attendance'],
ax=ax02,
kde=False,
norm_hist=True,
bins=bins)
ax02.set_title(label="Attendance per Month", fontsize=25)
ax02.set_xlabel('Attendance (# of people)', fontsize=20)
ax02.set_ylabel('Percent per person', fontsize=20)
ax02.tick_params(labelsize=15)
ax02.legend(months, loc="upper right", fontsize=15)
grouped = train[['Month', 'Attendance']].groupby('Month').mean()
order = [
'October', 'November', 'December', 'January', 'February', 'March',
'April', 'May', 'June'
]
sns.barplot(x='Attendance',
y=grouped.index,
data=grouped,
order=order,
ci=None,
orient='h',
saturation=1,
ax=ax21,
palette=sns.color_palette("cubehelix", 9))
ax21.set_xlim(16500, 20000)
ax21.set_xticks(range(16500, 20001, 500))
ax21.set_xlabel('Average Attendance (# of people)', fontsize=20)
ax21.set_ylabel('Month', fontsize=20)
ax21.tick_params(labelsize=15)
ax21.set_title(label="Average Attendance per Month", fontsize=25)
train['Year'] = train.index.year
grouped = train[['Year', 'Attendance']].groupby('Year').mean()
order = np.sort(train.index.year.unique())
sns.barplot(x='Attendance',
y=grouped.index,
data=grouped,
order=order,
ci=None,
orient='h',
saturation=1,
ax=ax22,
palette=sns.color_palette("cubehelix", 13))
ax22.set_xlim(16500, 18500)
ax22.set_xticks(range(16500, 18501, 500))
ax22.set_xlabel('Average Attendance (# of people)', fontsize=20)
ax22.set_ylabel('Year', fontsize=20)
ax22.tick_params(labelsize=15)
ax22.set_title(label="Average Attendance per Year", fontsize=25)
years = np.arange(
max(train['Year'].values) - 4,
max(train['Year'].values) + 1)
for year in years:
sns.distplot(train.loc[train.index.year == year]['Attendance'],
ax=ax03,
kde=False,
norm_hist=True,
bins=bins)
ax03.set_title(label="Attendance per Year", fontsize=25)
ax03.set_xlabel('Attendance (# of people)', fontsize=20)
ax03.set_ylabel('Percent per person', fontsize=20)
ax03.tick_params(labelsize=15)
ax03.legend(years, loc="upper right", fontsize=20)
for j in [0, 1]:
sns.distplot(train.loc[train['Playoffs?'] == j]['Attendance'],
ax=ax10,
kde=False,
norm_hist=True,
bins=bins)
ax10.set_title(label="Attendance for Regular and Playoff Games",
fontsize=25)
ax10.set_xlabel('Attendance (# of people)', fontsize=20)
ax10.set_ylabel('Percent per person', fontsize=20)
ax10.tick_params(labelsize=15)
ax10.legend(['Regular Season', 'Playoffs'], loc="upper right", fontsize=15)
win_percent = np.arange(0, 1, 0.10)
for i in win_percent:
sns.distplot(
train.loc[(train['Curr Win %'] >= i)
& (train['Curr Win %'] < i + 0.1)]['Attendance'],
ax=ax11,
kde=False,
norm_hist=True,
bins=bins)
ax11.set_title(label="Attendance for Different Win Percentages",
fontsize=25)
ax11.set_xlabel('Attendance (# of people)', fontsize=20)
ax11.set_ylabel('Percent per person', fontsize=20)
ax11.tick_params(labelsize=15)
ax11.legend([
'0 %', '10 %', '20 %', '30 %', '40 %', '50 %', '60 %', '70 %', '80 %',
'90 %', '100 %'
],
loc="upper right",
fontsize=17)
last_five = np.arange(0, 6)
for i in last_five:
sns.distplot(train.loc[train['Last Five'] == i]['Attendance'],
ax=ax12,
kde=False,
norm_hist=True,
bins=bins)
ax12.set_title(label="Attendance by Last Five Record", fontsize=25)
ax12.set_xlabel('Attendance (# of people)', fontsize=20)
ax12.set_ylabel('Percent per person', fontsize=20)
ax12.tick_params(labelsize=15)
ax12.legend(['0 Wins', '1 Win', '2 Wins', "3 Wins", "4 Wins", "5 Wins"],
loc="upper right",
fontsize=20)
grouped = train[['Last Five', 'Attendance']].groupby('Last Five').mean()
order = np.arange(0, 6)
sns.barplot(x='Attendance',
y=grouped.index,
data=grouped,
order=order,
ci=None,
orient='h',
saturation=1,
ax=ax31,
palette=sns.color_palette("cubehelix", 5))
ax31.set_xlim(16500, 18500)
ax31.set_xticks(range(16500, 18501, 500))
ax31.set_xlabel('Average Attendance (# of people)', fontsize=20)
ax31.set_ylabel('Record Over Last Five Games', fontsize=20)
ax31.tick_params(labelsize=15)
ax31.set_title(label="Average Attendance per Last Five Record",
fontsize=25)
num_numerical = ds.get_number_numerical()[name]
train_num = train.iloc[:, 0:num_numerical]
heat = sns.heatmap(train_num.corr(),
annot=True,
ax=ax13,
fmt='.2f',
cbar=True,
square=True,
xticklabels=True,
yticklabels=True,
annot_kws={'size': 16},
cmap='coolwarm',
center=0,
vmin=-1,
vmax=1,
cbar_kws={"shrink": 1})
ax13.set_title('Heatmap of Numerical Variable Correlation', size=25)
ax13.set_xticklabels(ax13.xaxis.get_majorticklabels(),
rotation=60,
size=15)
ax13.set_yticklabels(ax13.yaxis.get_majorticklabels(), rotation=0, size=15)
ax13.collections[0].colorbar.ax.tick_params(labelsize=15)
# Make annotations larger if abs(correlation) above 0.2
num_corrs = len(np.unique(train_num.corr().values.flatten()))
bigs = []
for i in np.arange(2, num_corrs + 1):
val = round(
np.sort(np.abs(np.unique(train_num.corr().values.flatten())))[-i],
2)
if val > 0.2:
bigs = np.append(bigs, val)
for text in heat.texts:
num = pd.to_numeric(text.get_text())
i = np.where(bigs == abs(num))[0]
if i.size > 0:
text.set_color('white')
text.set_size(27 - (i[0] * 3))
train.loc[train['Playoffs?'] == 0, "Playoffs?"] = 'Regular Season'
train.loc[train['Playoffs?'] == 1, "Playoffs?"] = 'Playoffs'
grouped = train[['Playoffs?', 'Attendance']].groupby('Playoffs?').mean()
order = ['Regular Season', 'Playoffs']
sns.barplot(x='Attendance',
y=grouped.index,
data=grouped,
order=order,
ci=None,
orient='h',
saturation=1,
ax=ax23,
palette=sns.color_palette("cubehelix", 5))
ax23.set_xlim(16500, 19500)
ax23.set_xticks(range(16500, 19501, 500))
ax23.set_xlabel('Average Attendance (# of people)', fontsize=20)
ax23.set_ylabel('Game Type', fontsize=20)
ax23.tick_params(labelsize=15)
ax23.set_title(label="Average Attendance per Game Type", fontsize=25)
train[['Curr Win %']] = np.round(train[['Curr Win %']], 1) * 100
grouped = train[['Curr Win %', 'Attendance']].groupby('Curr Win %').mean()
order = np.arange(0, 101, 10)
sns.barplot(x='Attendance',
y=grouped.index,
data=grouped,
order=order,
ci=None,
orient='h',
saturation=1,
ax=ax30,
palette=sns.color_palette("cubehelix", 5))
ax30.set_xlim(16500, 19500)
ax30.set_xticks(range(16500, 19501, 500))
ax30.set_xlabel('Average Attendance (# of people)', fontsize=20)
ax30.set_ylabel('Current Win %', fontsize=20)
ax30.tick_params(labelsize=15)
ax30.set_title(label="Average Attendance per Current Win %", fontsize=25)
# ax[3][2] = sns.pairplot(data = train_num)
# ax[3][2].set_title('Pairplot of Numerical Variable Correlation', size=25)
# ax[3][2].set_xticklabels(ax[3][2].xaxis.get_majorticklabels(), rotation=60, size = 15)
# ax[3][2].set_yticklabels(ax[3][2].yaxis.get_majorticklabels(), rotation=0, size = 15)
gs.tight_layout(fig)
# plt.tight_layout()
plt.show()
if save:
to_save = Path().resolve().joinpath('visualizations',
'all_plots_{}.png'.format(name))
fig.savefig(to_save, dpi=300)
