import pandas as pd
import numpy as np
from xgboost import XGBClassifier
from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
import seaborn as sns

#load the data
from google.colab import files
uploaded = files.upload()

parkinsons.data(n/a) - 40697 bytes, last modified: n/a - 100% done

#load the data into a data frame
df = pd.read_csv('parkinsons.data')
df.head()

#get the artcile
article = Article('https://www.mayoclinic.org/diseases-conditions/chronic-kidney-disease/symptoms-causes/syc-20354521')
article.download()
article.parse()

article.nlp()
corpus = article.text

#Check this data for missing values
df.isnull().values.any()

df.shape

#Get the target count
df['status'].value_counts()

percent_has_disease = 147 / (147 + 48) * 100
percent_dont_have_disease = 48 / (147 + 48) * 100
print('If I guess the individual did not have Parkinsons disease,
 I would be correct ', percent_dont_have_disease, '% of the time.')
print('If I guess the individual have Parkinsons disease, I would be correct ',
 percent_has_disease, '% of the time.')

dir="ltr">#Visualize the count
dir="ltr">sns.countplot(df['status'])

#Get the data types
df.dtypes

#Create the feature data set
X = df.drop(['name'],1)
X = np.array(X.drop(['status'],1))
#Create the target data set
y = np.array(df['status'])