import ray
ray.init()

@ray.remote
def f(x):
    return x * x

futures = [f.remote(i) for i in range(4)]
print(ray.get(futures))

import ray
ray.init()

@ray.remote
class Counter(object):
    def __init__(self):
        self.n = 0

    def increment(self):
        self.n  = 1

    def read(self):
        return self.n

counters = [Counter.remote() for i in range(4)]
[c.increment.remote() for c in counters]
futures = [c.read.remote() for c in counters]
print(ray.get(futures))

from ray import tune


def objective(step, alpha, beta):
    return (0.1   alpha * step / 100)**(-1)   beta * 0.1


def training_function(config):
    # Hyperparameters
    alpha, beta = config["alpha"], config["beta"]
    for step in range(10):
        # Iterative training function - can be any arbitrary training procedure.
        intermediate_score = objective(step, alpha, beta)
        # Feed the score back back to Tune.
        tune.report(mean_loss=intermediate_score)


analysis = tune.run(
    training_function,
    config={
        "alpha": tune.grid_search([0.001, 0.01, 0.1]),
        "beta": tune.choice([1, 2, 3])
    })

print("Best config: ", analysis.get_best_config(metric="mean_loss", mode="min"))

# Get a dataframe for analyzing trial results.
df = analysis.results_df

import gym
from ray.rllib.agents.ppo import PPOTrainer


# Define your problem using python and openAI's gym API:
class SimpleCorridor(gym.Env):
    """Corridor in which an agent must learn to move right to reach the exit.

    ---------------------
    | S | 1 | 2 | 3 | G |   S=start; G=goal; corridor_length=5
    ---------------------

    Possible actions to chose from are: 0=left; 1=right
    Observations are floats indicating the current field index, e.g. 0.0 for
    starting position, 1.0 for the field next to the starting position, etc..
    Rewards are -0.1 for all steps, except when reaching the goal ( 1.0).
    """

    def __init__(self, config):
        self.end_pos = config["corridor_length"]
        self.cur_pos = 0
        self.action_space = gym.spaces.Discrete(2)  # left and right
        self.observation_space = gym.spaces.Box(0.0, self.end_pos, shape=(1,))

    def reset(self):
        """Resets the episode and returns the initial observation of the new one.
        """
        self.cur_pos = 0
        # Return initial observation.
        return [self.cur_pos]

    def step(self, action):
        """Takes a single step in the episode given `action`

        Returns:
            New observation, reward, done-flag, info-dict (empty).
        """
        # Walk left.
        if action == 0 and self.cur_pos > 0:
            self.cur_pos -= 1
        # Walk right.
        elif action == 1:
            self.cur_pos  = 1
        # Set `done` flag when end of corridor (goal) reached.
        done = self.cur_pos >= self.end_pos
        #  1 when goal reached, otherwise -1.
        reward = 1.0 if done else -0.1
        return [self.cur_pos], reward, done, {}


# Create an RLlib Trainer instance.
trainer = PPOTrainer(
    config={
        # Env class to use (here: our gym.Env sub-class from above).
        "env": SimpleCorridor,
        # Config dict to be passed to our custom env's constructor.
        "env_config": {
            # Use corridor with 20 fields (including S and G).
            "corridor_length": 20
        },
        # Parallelize environment rollouts.
        "num_workers": 3,
    })

# Train for n iterations and report results (mean episode rewards).
# Since we have to move at least 19 times in the env to reach the goal and
# each move gives us -0.1 reward (except the last move at the end:  1.0),
# we can expect to reach an optimal episode reward of -0.1*18   1.0 = -0.8
for i in range(5):
    results = trainer.train()
    print(f"Iter: {i}; avg. reward={results['episode_reward_mean']}")

# Perform inference (action computations) based on given env observations.
# Note that we are using a slightly different env here (len 10 instead of 20),
# however, this should still work as the agent has (hopefully) learned
# to "just always walk right!"
env = SimpleCorridor({"corridor_length": 10})
# Get the initial observation (should be: [0.0] for the starting position).
obs = env.reset()
done = False
total_reward = 0.0
# Play one episode.
while not done:
    # Compute a single action, given the current observation
    # from the environment.
    action = trainer.compute_single_action(obs)
    # Apply the computed action in the environment.
    obs, reward, done, info = env.step(action)
    # Sum up rewards for reporting purposes.
    total_reward  = reward
# Report results.
print(f"Played 1 episode; total-reward={total_reward}")

import pickle
import requests

from sklearn.datasets import load_iris
from sklearn.ensemble import GradientBoostingClassifier

from ray import serve

serve.start()

# Train model.
iris_dataset = load_iris()
model = GradientBoostingClassifier()
model.fit(iris_dataset["data"], iris_dataset["target"])

@serve.deployment(route_prefix="/iris")
class BoostingModel:
    def __init__(self, model):
        self.model = model
        self.label_list = iris_dataset["target_names"].tolist()

    async def __call__(self, request):
        payload = await request.json()["vector"]
        print(f"Received flask request with data {payload}")

        prediction = self.model.predict([payload])[0]
        human_name = self.label_list[prediction]
        return {"result": human_name}


# Deploy model.
BoostingModel.deploy(model)

# Query it!
sample_request_input = {"vector": [1.2, 1.0, 1.1, 0.9]}
response = requests.get("http://localhost:8000/iris", json=sample_request_input)
print(response.text)
# Result:
# {
#  "result": "versicolor"
# }