使用 CnosDB 与 TensorFlow 进行时间序列预测

Filename: SN_m_tot_V2.0.csv
Format: Comma Separated values (adapted for import in spreadsheets)
The separator is the semicolon ';'.
Contents:
Column 1-2: Gregorian calendar date
- Year
- Month
Column 3: Date in fraction of year.
Column 4: Monthly mean total sunspot number.
Column 5: Monthly mean standard deviation of the input sunspot numbers.
Column 6: Number of observations used to compute the monthly mean total sunspot number.
Column 7: Definitive/provisional marker. '1' indicates that the value is definitive. '0' indicates that the value is still provisional.

import pandas as pd
df = pd.read_csv("SN_m_tot_V2.0.csv", sep=";", header=None)
df.columns = ["year", "month", "date_fraction", "mssn", "standard_deviation", "observations", "marker"]
# convert year and month to strings
df["year"] = df["year"].astype(str)
df["month"] = df["month"].astype(str)
# concatenate year and month
df["date"] = df["year"] + "-" + df["month"]
df.head()

import matplotlib.pyplot as plt 
df["Date"] = pd.to_datetime(df["date"], format="%Y-%m")
plt.plot(df["Date"], df["mssn"])
plt.xlabel("Date")
plt.ylabel("MSSN")
plt.title("Sunspot Activity Over Time")
plt.show()

(base) root@ecs-django-dev:~# docker run --restart=always --name cnosdb -d --env cpu=2 --env memory=4 -p 31007:31007 cnosdb/cnosdb:v2.0.2.1-beta
(base) root@ecs-django-dev:~# docker exec -it cnosdb sh sh
# cnosdb-cli
CnosDB CLI v2.0.0
Input arguments: Args { host: "0.0.0.0", port: 31007, user: "cnosdb", password: None, database: "public", target_partitions: None, data_path: None, file: [], rc: None, format: Table, quiet: false }

public ❯ CREATE TABLE sunspot (
date STRING,
    mssn DOUBLE,
);
Query took 0.002 seconds.
public ❯ SHOW TABLES;
+---------+
| Table   |
+---------+
| sunspot |
+---------+
Query took 0.001 seconds.
public ❯ SELECT * FROM sunspot;
+------+------+------+
| time | date | mssn |
+------+------+------+
+------+------+------+
Query took 0.002 seconds.

# 安装 Python Connector
pip install -U cnos-connector

from cnosdb_connector import connect
conn = connect(url="http://127.0.0.1:31001/", user="root", password="")
cursor = conn.cursor()

# 创建 tf_demo database
conn.create_database("tf_demo")
# 使用 tf_demo database
conn.switch_database("tf_demo")
print(conn.list_database())
cursor.execute("CREATE TABLE sunspot (date STRING, mssn DOUBLE,);")
print(conn.list_table())

[{'Database': 'tf_demo'}, {'Database': 'usage_schema'}, {'Database': 'public'}]
[{'Table': 'sunspot'}]

### df 为pandas的dataframe，"sunspot"为CnosDB中的表名，['date', 'mssn']为需要写入的列的名字
### 如果写入的列不包含时间列，将会根据当前时间自动生成
conn.write_dataframe(df, "sunspot", ['date', 'mssn'])

df = pd.read_sql("select * from sunspot;", conn)
print(df.head())

import numpy as np
# Convert the data values to numpy for better and faster processing
time_index = np.array(df['date'])
data = np.array(df['mssn'])   
# ratio to split the data
SPLIT_RATIO = 0.8
# Dividing into train-test split
split_index = int(SPLIT_RATIO * data.shape[0])   
# Train-Test Split
train_data = data[:split_index]
train_time = time_index[:split_index]  
test_data = data[split_index:]
test_time = time_index[split_index:]

import tensorflow as tf
## required parameters
WINDOW_SIZE = 60
BATCH_SIZE = 32
SHUFFLE_BUFFER = 1000
## function to create the input features
def ts_data_generator(data, window_size, batch_size, shuffle_buffer):
'''
    Utility function for time series data generation in batches
    '''
    ts_data = tf.data.Dataset.from_tensor_slices(data)
    ts_data = ts_data.window(window_size + 1, shift=1, drop_remainder=True)
    ts_data = ts_data.flat_map(lambda window: window.batch(window_size + 1))
    ts_data = ts_data.shuffle(shuffle_buffer).map(lambda window: (window[:-1], window[-1]))
    ts_data = ts_data.batch(batch_size).prefetch(1)
return ts_data# Expanding data into tensors
# Expanding data into tensors
tensor_train_data = tf.expand_dims(train_data, axis=-1)
tensor_test_data = tf.expand_dims(test_data, axis=-1)
## generate input and output features for training and testing set
tensor_train_dataset = ts_data_generator(tensor_train_data, WINDOW_SIZE, BATCH_SIZE, SHUFFLE_BUFFER)
tensor_test_dataset = ts_data_generator(tensor_test_data, WINDOW_SIZE, BATCH_SIZE, SHUFFLE_BUFFER)

model = tf.keras.models.Sequential([
                            tf.keras.layers.Conv1D(filters=128, kernel_size=3, strides=1, input_shape=[None, 1]),
                            tf.keras.layers.MaxPool1D(pool_size=2, strides=1),
                          tf.keras.layers.LSTM(128, return_sequences=True),
                          tf.keras.layers.LSTM(64, return_sequences=True),  
                          tf.keras.layers.Dense(132, activatinotallow="relu"),  
                          tf.keras.layers.Dense(1)])

## compile neural network model
optimizer = tf.keras.optimizers.Adam(learning_rate=1e-3)
model.compile(loss="mse",
            optimizer=optimizer,
            metrics=["mae"])
## training neural network model
history = model.fit(tensor_train_dataset, epochs=20, validation_data=tensor_test_dataset)

# summarize history for loss
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()

def model_forecast(model, data, window_size):
ds = tf.data.Dataset.from_tensor_slices(data)
ds = ds.window(window_size, shift=1, drop_remainder=True)
ds = ds.flat_map(lambda w: w.batch(window_size))
ds = ds.batch(32).prefetch(1)
forecast = model.predict(ds)
return forecast
rnn_forecast = model_forecast(model, data[..., np.newaxis], WINDOW_SIZE)
rnn_forecast = rnn_forecast[split_index - WINDOW_SIZE:-1, -1, 0]
# Overall Error
error = tf.keras.metrics.mean_absolute_error(test_data, rnn_forecast).numpy()
print(error)

101/101 [==============================] - 2s 18ms/step
24.676455

plt.plot(test_data)
plt.plot(rnn_forecast)
plt.title('MSSN Forecast')
plt.ylabel('MSSN')
plt.xlabel('Month')
plt.legend(['Ground Truth', 'Predictions'], loc='upper right')
plt.show()