Stop tracking sigllm/sigllm.ipynb

setup.py

@@ -12,7 +12,8 @@
     history = history_file.read()
 
 install_requires = [
-    'numpy', 'openai', 'pandas','orion', #'collections'
+    'numpy', 'openai', 'pandas','orion', 'matplotlib', 'scikit-learn',
+    'tiktoken',
 ]
 
 setup_requires = [

sigllm/anomalies.py

@@ -0,0 +1,132 @@
+# -*- coding: utf-8 -*-
+
+"""
+Result post-processing module.
+
+This module contains functions that help convert model responses back to indices and timestamps.
+"""
+import numpy as np
+
+
+def str2sig(text, sep=',', decimal=0):
+    """Convert a text string to a signal.
+
+    Convert a string containing digits into an array of numbers.
+
+    Args:
+        text (str):
+            A string containing signal values.
+        sep (str):
+            String that was used to separate each element in text, Default to `","`.
+        decimal (int):
+            Number of decimal points to shift each element in text to. Default to `0`.
+
+    Returns:
+        numpy.ndarray:
+            A 1-dimensional array containing parsed elements in `text`.
+    """
+    # Remove all characters from text except the digits and sep and decimal point
+    text = ''.join(i for i in text if (i.isdigit() or i == sep or i == '.'))
+    values = np.fromstring(text, dtype=float, sep=sep)
+    return values * 10**(-decimal)
+
+
+def str2idx(text, len_seq, sep=','):
+    """Convert a text string to indices.
+
+    Convert a string containing digits into an array of indices.
+
+    Args:
+        text (str):
+            A string containing indices values.
+        len_seq (int):
+            The length of processed sequence
+        sep (str):
+            String that was used to separate each element in text, Default to `","`.
+
+    Returns:
+        numpy.ndarray:
+            A 1-dimensional array containing parsed elements in `text`.
+    """
+    # Remove all characters from text except the digits and sep
+    text = ''.join(i for i in text if (i.isdigit() or i == sep))
+
+    values = np.fromstring(text, dtype=int, sep=sep)
+
+    # Remove indices that exceed the length of sequence
+    values = values[values < len_seq]
+    return values
+
+
+def get_anomaly_list_within_seq(res_list, alpha=0.5):
+    """Get the final list of anomalous indices of a sequence
+
+    Choose anomalous index in the sequence based on multiple LLM responses
+
+    Args:
+        res_list (List[numpy.ndarray]):
+            A list of 1-dimensional array containing anomous indices output by LLM
+        alpha (float):
+            Percentage of votes needed for an index to be deemed anomalous. Default: 0.5
+
+    Returns:
+        numpy.ndarray:
+            A 1-dimensional array containing final anomalous indices
+    """
+    min_vote = np.ceil(alpha * len(res_list))
+
+    flattened_res = np.concatenate(res_list)
+
+    unique_elements, counts = np.unique(flattened_res, return_counts=True)
+
+    final_list = unique_elements[counts >= min_vote]
+
+    return final_list
+
+
+def merge_anomaly_seq(anomalies, start_indices, window_size, step_size, beta=0.5):
+    """Get the final list of anomalous indices of a sequence when merging all rolling windows
+
+    Args:
+        anomalies (List[numpy.ndarray]):
+            A list of 1-dimensional array containing anomous indices of each window
+        start_indices (numpy.ndarray):
+            A 1-dimensional array contaning the first index of each window
+        window_size (int):
+            Length of each window
+        step_size (int):
+            Indicating the number of steps the window moves forward each round.
+        beta (float):
+            Percentage of containing windows needed for index to be deemed anomalous. Default: 0.5
+
+    Return:
+        numpy.ndarray:
+            A 1-dimensional array containing final anomalous indices
+    """
+    anomalies = [arr + first_idx for (arr, first_idx) in zip(anomalies, start_indices)]
+
+    min_vote = np.ceil(beta * window_size / step_size)
+
+    flattened_res = np.concatenate(anomalies)
+
+    unique_elements, counts = np.unique(flattened_res, return_counts=True)
+
+    final_list = unique_elements[counts >= min_vote]
+
+    return np.sort(final_list)
+
+
+def idx2time(sequence, idx_list):
+    """Convert list of indices into list of timestamp
+
+    Args:
+        sequence (pandas.Dataframe):
+            Signal with timestamps and values
+        idx_list (numpy.ndarray):
+            A 1-dimensional array of indices
+
+    Returns:
+        numpy.ndarray:
+            A 1-dimensional array containing timestamps
+    """
+    return sequence.iloc[idx_list].timestamp.to_numpy()

sigllm/data.py

@@ -3,17 +3,16 @@
 """
 Data preprocessing module.
 
-This module contains functions that help convert timeseries into string, preparing it for a language model.
+This module contains functions that prepare timeseries for a language model.
 """
 
 import numpy as np
 
+
 def rolling_window_sequences(X, index, window_size, step_size):
     """Create rolling window sequences out of time series data.
 
-    The function creates an array of input sequences and an array of target sequences by rolling
-    over the input sequence with a specified window.
-    Optionally, certain values can be dropped from the sequences.
+    The function creates an array of sequences by rolling over the input sequence.
 
     Args:
         X (ndarray):
@@ -44,21 +43,23 @@ def rolling_window_sequences(X, index, window_size, step_size):
     return np.asarray(out_X), np.asarray(X_index)
 
 
-def sig2str(values, sep=',', space=False, decimal=0):
+def sig2str(values, sep=',', space=False, decimal=0, rescale=True):
     """Convert a signal to a string.
 
     Convert a 1-dimensional time series into text by casting and rescaling it
-    to nonnegative integer values then into a string.
+    to nonnegative integer values then into a string (optional).
 
     Args:
         values (numpy.ndarray):
             A sequence of signal values.
         sep (str):
-            String to separate each element in values, Default to `","`.
+            String to separate each element in values. Default to `","`.
         space (bool):
             Whether to add space between each digit in the result. Default to `False`.
         decimal (int):
             Number of decimal points to keep from the float representation. Default to `0`.
+        rescale(bool):
+            Whether to rescale the time series. Default to `True`
 
     Returns:
         str:
@@ -68,12 +69,13 @@ def sig2str(values, sep=',', space=False, decimal=0):
     values = np.abs(values)
 
     sequence = sign * (values * 10**decimal).astype(int)
-
-    #Rescale all elements to be nonnegative
-    sequence = sequence - min(sequence)
+
+    # Rescale all elements to be nonnegative
+    if rescale:
+        sequence = sequence - min(sequence)
 
     res = sep.join([str(num) for num in sequence])
     if space:
         res = ' '.join(res)
 
-    return res
+    return res

sigllm/gpt.py

@@ -5,48 +5,57 @@
 
 This module contains functions that are specifically used for GPT models
 """
+import os
+
+from openai import OpenAI
 
-import openai
 
-with open("../gpt_model/openai_api_key.txt", "r") as f:
-    api_key = f.read()
-
 def load_system_prompt(file_path):
     with open(file_path) as f:
         system_prompt = f.read()
     return system_prompt
 
-GPT_model = "gpt-3.5-turbo" #"gpt-4"
 
-client = openai.Client(api_key=api_key)
+CURRENT_DIR = os.path.dirname(os.path.abspath(__file__))
+
+ZERO_SHOT_FILE = 'gpt_system_prompt_zero_shot.txt'
+ONE_SHOT_FILE = 'gpt_system_prompt_one_shot.txt'
+
+ZERO_SHOT_DIR = os.path.join(CURRENT_DIR, "..", "template", ZERO_SHOT_FILE)
+ONE_SHOT_DIR = os.path.join(CURRENT_DIR, "..", "template", ONE_SHOT_FILE)
+
+
+GPT_model = "gpt-4"  # "gpt-4-0125-preview" #  #  #"gpt-3.5-turbo" #
+client = OpenAI()
+
 
 def get_gpt_model_response(message, gpt_model=GPT_model):
     completion = client.chat.completions.create(
-    model=gpt_model,
-    messages=message,
+        model=gpt_model,
+        messages=message,
     )
     return completion.choices[0].message.content
 
-def create_message_zero_shot(seq_query, system_prompt_file='../gpt_model/system_prompt_zero_shot.txt'):
+
+def create_message_zero_shot(seq_query, system_prompt_file=ZERO_SHOT_DIR):
     messages = []
-    
-    messages.append({"role": "system", "content":load_system_prompt(system_prompt_file)})
+
+    messages.append({"role": "system", "content": load_system_prompt(system_prompt_file)})
 
     # final prompt
     messages.append({"role": "user", "content": f"Sequence: {seq_query}"})
     return messages
 
 
-def create_message_one_shot(seq_query, seq_ex, ano_ind_ex, system_prompt_file='../gpt_model/system_prompt_one_shot.txt'):
+def create_message_one_shot(seq_query, seq_ex, ano_idx_ex, system_prompt_file=ONE_SHOT_DIR):
     messages = []
-    
-    messages.append({"role": "system", "content":load_system_prompt(system_prompt_file)})
+
+    messages.append({"role": "system", "content": load_system_prompt(system_prompt_file)})
 
     # one shot
     messages.append({"role": "user", "content": f"Sequence: {seq_ex}"})
-    messages.append({"role": "assistant", "content": ano_ind_ex})
+    messages.append({"role": "assistant", "content": ano_idx_ex})
 
     # final prompt
     messages.append({"role": "user", "content": f"Sequence: {seq_query}"})
     return messages
-