MachineLearningBegginer

//Importing Libraries

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
%matplotlib inline

//Import CSV File
data_frame = pd.read_csv('pima-data.csv')

//Check CSV File
data_frame.shape
data_frame.head(3)
data_frame.tail(4)

//Check If Any Data Contains Null
print(data_frame.isnull().values.any())

//Correlation HeatMap
# Here size means plot-size
def corr_heatmap(data_frame, size=11):
  # Getting correlation using Pandas
  correlation = data_frame.corr()

  # Dividing the plot into subplots for increasing size of plots
  fig, heatmap = plt.subplots(figsize=(size, size))

  # Plotting the correlation heatmap
  heatmap.matshow(correlation)

  # Adding xticks and yticks
  plt.xticks(range(len(correlation.columns)), correlation.columns)
  plt.yticks(range(len(correlation.columns)), correlation.columns)

  # Displaying the graph
  plt.show()
  
corr_heatmap(data_frame, 12)

//Clean same type data
# Deleting 'skin' column completely
del data_frame['skin']
# Checking if the action was successful or not
data_frame.head()

//Mapping bool to int
# Mapping the values
map_diabetes = {True : 1, False : 0}

# Setting the map to the data_frame
data_frame['diabetes'] = data_frame['diabetes'].map(map_diabetes)

# Let's see what we have done
data_frame.head()