avisheknag17

import pandas as pd

brainwave_df = pd.read_csv('../data/emotions.csv', index_col=False)
brainwave_df.head()

avisheknag17

import seaborn as sns
import matplotlib.pyplot as plt

plt.figure(figsize=(12,5))
sns.countplot(x=brainwave_df.label, color='mediumseagreen')
plt.title('Emotional sentiment class distribution', fontsize=16)
plt.ylabel('Class Counts', fontsize=16)
plt.xlabel('Class Label', fontsize=16)
plt.xticks(rotation='vertical');

avisheknag17

%%time
from sklearn.pipeline import Pipeline
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import cross_val_score, train_test_split

pl_random_forest = Pipeline(steps=[('random_forest', RandomForestClassifier())])
scores = cross_val_score(pl_random_forest, brainwave_df, label_df, cv=10,scoring='accuracy')
print('Accuracy for RandomForest : ', scores.mean())

avisheknag17

%%time

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression

pl_log_reg = Pipeline(steps=[('scaler',StandardScaler()),
                             ('log_reg', LogisticRegression(multi_class='multinomial', solver='saga', max_iter=200))])
scores = cross_val_score(pl_log_reg, brainwave_df, label_df, cv=10,scoring='accuracy')
print('Accuracy for Logistic Regression: ', scores.mean())

avisheknag17

from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
scaled_df = scaler.fit_transform(brainwave_df)
pca = PCA(n_components = 20)
pca_vectors = pca.fit_transform(scaled_df)
for index, var in enumerate(pca.explained_variance_ratio_):
    print("Explained Variance ratio by Principal Component ", (index+1), " : ", var)

avisheknag17

%%time

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression

pl_log_reg_pca = Pipeline(steps=[('scaler',StandardScaler()),
                             ('pca', PCA(n_components = 2)),
                             ('log_reg', LogisticRegression(multi_class='multinomial', solver='saga', max_iter=200))])
scores = cross_val_score(pl_log_reg_pca, brainwave_df, label_df, cv=10,scoring='accuracy')

avisheknag17

%%time

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression

pl_log_reg_pca_10 = Pipeline(steps=[('scaler',StandardScaler()),
                             ('pca', PCA(n_components = 10)),
                             ('log_reg', LogisticRegression(multi_class='multinomial', solver='saga', max_iter=200))])
scores = cross_val_score(pl_log_reg_pca_10, brainwave_df, label_df, cv=10,scoring='accuracy')

avisheknag17

%%time

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.neural_network import MLPClassifier

pl_mlp = Pipeline(steps=[('scaler',StandardScaler()),
                             ('mlp_ann', MLPClassifier(hidden_layer_sizes=(1275, 637)))])
scores = cross_val_score(pl_mlp, brainwave_df, label_df, cv=10,scoring='accuracy')
print('Accuracy for ANN : ', scores.mean())

avisheknag17

%%time

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.svm import LinearSVC

pl_svm = Pipeline(steps=[('scaler',StandardScaler()),
                             ('pl_svm', LinearSVC())])
scores = cross_val_score(pl_svm, brainwave_df, label_df, cv=10,scoring='accuracy')
print('Accuracy for Linear SVM : ', scores.mean())

avisheknag17

%%time

import xgboost as xgb

pl_xgb = Pipeline(steps=
                  [('xgboost', xgb.XGBClassifier(objective='multi:softmax'))])
scores = cross_val_score(pl_xgb, brainwave_df, label_df, cv=10)
print('Accuracy for XGBoost Classifier : ', scores.mean())