How To Get Started with a Predictive Machine Learning Program in Python in 5 Easy Steps

pip install sklearn

Collecting sklearn
  Downloading sklearn-0.0.tar.gz (1.1 kB)
Collecting scikit-learn
  Downloading scikit_learn-0.23.1-cp38-cp38-macosx_10_9_x86_64.whl (7.2 MB)
     |████████████████████████████████| 7.2 MB 5.0 MB/s 
Collecting numpy>=1.13.3
  Downloading numpy-1.18.4-cp38-cp38-macosx_10_9_x86_64.whl (15.2 MB)
     |████████████████████████████████| 15.2 MB 12.6 MB/s 
Collecting joblib>=0.11
  Downloading joblib-0.15.1-py3-none-any.whl (298 kB)
     |████████████████████████████████| 298 kB 8.1 MB/s 
Collecting threadpoolctl>=2.0.0
  Downloading threadpoolctl-2.1.0-py3-none-any.whl (12 kB)
Collecting scipy>=0.19.1
  Downloading scipy-1.4.1-cp38-cp38-macosx_10_9_x86_64.whl (28.8 MB)
     |████████████████████████████████| 28.8 MB 5.8 MB/s 
Using legacy setup.py install for sklearn, since package 'wheel' is not installed.
Installing collected packages: numpy, joblib, threadpoolctl, scipy, scikit-learn, sklearn
    Running setup.py install for sklearn ... done
Successfully installed joblib-0.15.1 numpy-1.18.4 scikit-learn-0.23.1 scipy-1.4.1 sklearn-0.0 threadpoolctl-2.1.0

negative = [
    "Protesters who were marching from Minneapolis to St. Paul were tear gassed by police as they tried to cross the Lake Street Marshall Bridge ",
    "The National Guard has been activated in Washington, D.C. to assist police handling protests around the White House",
    "Police have been firing tear gas at the protesters near the 5th Precinct in Minneapolis, where some in the crowd have responded with projectiles of their own",
    "Texas and Colorado have activated the National Guard respond to protests",
    "The mayor of Rochester, New York, has declared a state of emergency and ordered a curfew from 9 p.m. Saturday to 7 a.m. Sunday",
    "Cleveland, Ohio, has enacted a curfew that will go into effect at 8 p.m. Saturday and last through 8 a.m. Sunday",
    "A police car appears to be on fire in Los Angeles. Police officers are holding back a line of demonstrators to prevent them from getting close to the car."
            ]
positive = [
    "Two NASA astronauts make history with their successful launch into space aboard a SpaceX rocket",
    "After questionable weather, officials give the all clear for the SpaceX launch",
    "NASA astronauts Bob Behnken and Doug Hurley climb aboard SpaceX's Crew Dragon spacecraft as they prepare for a mission to the International Space Station",
    "New York Gov. Andrew Cuomo signs a bill giving death benefits to families of frontline workers who died battling the coronavirus pandemic"
]

def prepare_data(positive, negative):
    data = positive + negative
    target = [0]*len(positive) + [1]*len(negative)
    return {'data': data, 'target': target}

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.model_selection import train_test_split
def train_data_set(data_set):
    x_train, x_test, y_train, y_test = train_test_split(data_set['data'], data_set['target'])
    transfer = TfidfVectorizer()
    x_train = transfer.fit_transform(x_train)
    x_test = transfer.transform(x_test)
    estimator = MultinomialNB()
    estimator.fit(x_train, y_train)
    score = estimator.score(x_test, y_test)
    print("score：\n", score)
    return {'transfer': transfer, 'estimator': estimator}

import tweepy

def setup_twitter():
    consumer_key = "REPLACE WITH YOUR KEY"
    consumer_secret = "REPLACE WITH YOUR SECRET"
    access_token = "REPLACE WITH YOUR TOKEN"
    access_token_secret = "REPLACE WITH YOUR TOKEN SECRET"
    # authentication of consumer key and secret
    auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
    # authentication of access token and secret
    auth.set_access_token(access_token, access_token_secret)
    api = tweepy.API(auth)
    return api

def mood_on_cnn(api, predictor):
    stat = [0, 0]
    for status in tweepy.Cursor(api.user_timeline, screen_name='@cnnbrk', tweet_mode="extended").items():
        sentence_x = predictor['transfer'].transform([status.full_text])
        y_predict = predictor['estimator'].predict(sentence_x)
        stat[y_predict[0]] += 1
    return stat

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.model_selection import train_test_split
import tweepy

negative = [
    "Protesters who were marching from Minneapolis to St. Paul were tear gassed by police as they tried to cross the Lake Street Marshall Bridge ",
    "The National Guard has been activated in Washington, D.C. to assist police handling protests around the White House",
    "Police have been firing tear gas at the protesters near the 5th Precinct in Minneapolis, where some in the crowd have responded with projectiles of their own",
    "Texas and Colorado have activated the National Guard respond to protests",
    "The mayor of Rochester, New York, has declared a state of emergency and ordered a curfew from 9 p.m. Saturday to 7 a.m. Sunday",
    "Cleveland, Ohio, has enacted a curfew that will go into effect at 8 p.m. Saturday and last through 8 a.m. Sunday",
    "A police car appears to be on fire in Los Angeles. Police officers are holding back a line of demonstrators to prevent them from getting close to the car."
            ]
positive = [
    "Two NASA astronauts make history with their successful launch into space aboard a SpaceX rocket",
    "After questionable weather, officials give the all clear for the SpaceX launch",
    "NASA astronauts Bob Behnken and Doug Hurley climb aboard SpaceX's Crew Dragon spacecraft as they prepare for a mission to the International Space Station",
    "New York Gov. Andrew Cuomo signs a bill giving death benefits to families of frontline workers who died battling the coronavirus pandemic"
]

def prepare_data(positive, negative):
    data = positive + negative
    target = [0]*len(positive) + [1]*len(negative)
    return {'data': data, 'target': target}

def train_data_set(data_set):
    x_train, x_test, y_train, y_test = train_test_split(data_set['data'], data_set['target'])
    transfer = TfidfVectorizer()
    x_train = transfer.fit_transform(x_train)
    x_test = transfer.transform(x_test)
    estimator = MultinomialNB()
    estimator.fit(x_train, y_train)
    score = estimator.score(x_test, y_test)
    print("score：\n", score)
    return {'transfer': transfer, 'estimator': estimator}

def setup_twitter():
    consumer_key = "REPLACE WITH YOUR KEY"
    consumer_secret = "REPLACE WITH YOUR SECRET"
    access_token = "REPLACE WITH YOUR TOKEN"
    access_token_secret = "REPLACE WITH YOUR TOKEN SECRET"
    # authentication of consumer key and secret
    auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
    # authentication of access token and secret
    auth.set_access_token(access_token, access_token_secret)
    api = tweepy.API(auth)
    return api

def mood_on_cnn(api, predictor):
    stat = [0, 0]
    for status in tweepy.Cursor(api.user_timeline, screen_name='@cnnbrk', tweet_mode="extended").items():
        sentence_x = predictor['transfer'].transform([status.full_text])
        y_predict = predictor['estimator'].predict(sentence_x)
        stat[y_predict[0]] += 1
    return stat

data_set = prepare_data(positive, negative)
predictor = train_data_set(data_set)
api = setup_twitter()
stat = mood_on_cnn(api, predictor)
print(stat)
print("Mood (0 good, 1 bad)", stat[1]/(stat[0] + stat[1]))

score：
 1.0
[751, 2455]
Mood (0 good, 1 bad) 0.765751715533375