ml.py

# Load modules and dependancies library

from pandas import read_csv
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn.metrics import accuracy_score
import pandas as pd

# Load dataset
# load the data file as a Pandas data frame and analyze the data

df = pd.read_csv(r"D:\Python\durbar\iris.csv")

# Split-out validation dataset
# Split into training data and test data
# The training set contains a known output and the model learns on this data in order to be generalized # to other data later on
# We have the test dataset (or subset) in order to test our model’s prediction on this subset.

X = df[['sepal_length','sepal_width','petal_length','petal_width']]
y = df['classification']

# Now we can use the train_test_split function in order to make the split.
# The test_size=0.20 or 0.2 inside the function indicates the percentage of the data that should be 
# Create training and testing vars, It’s usually around 80/20 or 70/30.
X_train, X_test, Y_train, Y_test = train_test_split(X, y, test_size=0.20, random_state=1)


# Now we’ll fit the model on the training data:
# support vector clustering (SVC), select our algorithm

model = SVC(gamma='auto')
model.fit(X_train, Y_train)

# Make predictions on validation dataset
# We’re fitting the model on the training data and trying to predict the test data.
predictions = model.predict(X_test)

# Evaluate predictions
print(accuracy_score(Y_test, predictions))

# Pickle model 
# All pandas objects are equipped with to_pickle methods which use Python’s cPickle module to save data # structures to disk using the pickle format.
# Save a model in scikit-learn by using Python’s built-in persistence model
# Way to persist the model for future use without having to retrain.
pd.to_pickle(model,r'D:\Python\durbar\new_model.pickle')

# Unpickle model 
model = pd.read_pickle(r'D:\Python\durbar\new_model.pickle') 
# read a pickle pd.read_pickle('model.pkl')

# Take input from user
sepal_length = float(input("Enter sepal_length: "))
sepal_width = float(input("Enter sepa_width: "))
petal_length = float(input("Enter petal_length: "))
petal_width = float(input("Enter petal_width: "))

result = model.predict([[sepal_length,sepal_width,petal_length,petal_width]])  # input must be 2D array
print(result)