A simple example to create local predictions using a pre-built model

local_predictions.py

# import BigML class
from bigml.api import BigML

# import local Model class
from bigml.model import Model

# Instantiate the API with your credentials. You can avoid this if you set up your username and API key in your environment
api = BigML('yourusername', '3ff25044b4f4582903d90000a5fab240442e734c') 

# Get the model. Assuming that you already created in BigML
model = api.get_model('model/513fbf8a035d07361e000509') 

# Instantiate the local model
local_model = Model(model)

# Assuming that you have the data that you want to create predictions from in a csv file
file = open("your_file.csv" "U")

# File where you want to store the predictions
predictions = open("predictions.csv', "w")

#  Assuming that your csv file has a header that matches the one that you use to create the model
field_names = file.readline().strip().split(',') 

# Assuming that there's no missing values and all the values in your input are float.
for line in file:
    # parse each line in the file
    values = line.strip().split(',') 
    # convert string to values. Adapt it as you need it
    values = [float(value) for value in values]
    # creates a dictionary for the input data
    input_data = dict(zip(field_names, values))
    # creates a local prediction
    prediction = local_model.predict(input_data)
    # saves the prediction to a file
    predictions.write("%s\n" % prediction)
    predictions.flush()

# Close files
predictions.close()
file.close()