Davisy

import pandas as pd
from sklearn import linear_model
from sklearn.ensemble import VotingClassifier
from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer
from sklearn.model_selection import GridSearchCV
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import Pipeline

Y_COLUMN = "author"
TEXT_COLUMN = "text"

Davisy

# import important modules  
import pandas as pd 
import numpy as np 
import matplotlib.pyplot as plt 
import seaborn as sns  
plt.rcParams["axes.labelsize"] = 18 
import warnings 
warnings.filterwarnings('ignore') %matplotlib inline

Davisy

# Import data
data = pd.read_csv('../data/financial_inclusion.csv')

Davisy

# print shape 
print('train data shape :', data.shape)

Davisy

# Inspect Data by showing the first five rows 
data.head()

Davisy

## show Some information about the dataset 
print(data.info())

Davisy

# Frequency table of a variable will give us the count of each category in that Target variable.
data['bank_account'].value_counts()

Davisy

# Explore Target distribution 

sns.catplot(x="bank_account", kind="count", data= data)

Davisy

# Explore Country distribution 

sns.catplot(x="country", kind="count", data=data)

Davisy

# Explore Country distribution 

sns.catplot(x="country", kind="count", data=data)