dipanjanS

g = sns.FacetGrid(wines, col="res_sugar_labels", 
                  hue='wine_type')
g.map(plt.scatter, "fixed acidity", "alcohol", alpha=.7)
g.add_legend();

dipanjanS

# example depicting representing 3-D continous data
# using color and facets
quantile_list = [0, .25, .5, .75, 1.]
quantile_labels = ['0', '25', '50', '75']
wines['res_sugar_labels'] = pd.qcut(wines['residual sugar'], 
                                    q=quantile_list, labels=quantile_labels)
wines['alcohol_levels'] = pd.qcut(wines['alcohol'], 
                                    q=quantile_list, labels=quantile_labels)
g = sns.FacetGrid(wines, col="res_sugar_labels", 
                  hue='alcohol_levels')

dipanjanS

# using size for the 3rd dimension
sc = sns.scatterplot(wines['fixed acidity'], wines['alcohol'], 
                size=wines['residual sugar'])

# using color for the 3rd dimension
sc = sns.scatterplot(wines['fixed acidity'], wines['alcohol'], 
                hue=wines['residual sugar'], alpha=0.9)

dipanjanS

# facets with histograms
fig = plt.figure(figsize = (10,4))
title = fig.suptitle("Sulphates Content in Wine", fontsize=14)
fig.subplots_adjust(top=0.85, wspace=0.3)

ax1 = fig.add_subplot(1,2, 1)
ax1.set_title("Red Wine")
ax1.set_xlabel("Sulphates")
ax1.set_ylabel("Frequency") 
ax1.set_ylim([0, 1200])

dipanjanS

fig = plt.figure(figsize = (10, 4))
title = fig.suptitle("Wine Type - Quality", fontsize=14)
fig.subplots_adjust(top=0.85, wspace=0.3)

ax1 = fig.add_subplot(1,2, 1)
ax1.set_title("Red Wine")
ax1.set_xlabel("Quality")
ax1.set_ylabel("Frequency") 
rw_q = red_wine['quality'].value_counts()
rw_q = (list(rw_q.index), list(rw_q.values))

dipanjanS

fig = plt.figure(figsize = (6, 4))
title = fig.suptitle("Wine Quality Frequency", fontsize=14)
fig.subplots_adjust(top=0.85, wspace=0.3)

ax = fig.add_subplot(1,1, 1)
ax.set_xlabel("Quality")
ax.set_ylabel("Frequency") 
w_q = wines['quality'].value_counts()
w_q = (list(w_q.index), list(w_q.values))
ax.tick_params(axis='both', which='major', labelsize=8.5)

dipanjanS

from sklearn.metrics import classification_report

print(classification_report(y_true=test_sentiments, 
                            y_pred=predictions, target_names=LABELS))

dipanjanS

import seaborn as sns
import matplotlib.pyplot as plt

%matplotlib inline

with tf.Session() as session:
    cm = tf.confusion_matrix(test_sentiments, predictions).eval()

LABELS = ['negative', 'positive']
sns.heatmap(cm, annot=True, xticklabels=LABELS, yticklabels=LABELS, fmt='g')

dipanjanS

# get location of saved best model
best_model_dir = results_df[results_df['Test Accuracy'] == results_df['Test Accuracy'].max()]['Model Dir'].values[0]

# load up model
embedding_feature = hub.text_embedding_column(
        key='sentence', module_spec="https://tfhub.dev/google/universal-sentence-encoder/2", trainable=True)

dnn = tf.estimator.DNNClassifier(
            hidden_units=[512, 128],
            feature_columns=[embedding_feature],

dipanjanS

results_df = pd.DataFrame.from_dict(results, orient="index")
results_df