Learn to build large language model applications: vector databases, langchain, fine tuning and prompt engineering. Learn more

Time series data, a continuous stream of measurements captured over time, is the lifeblood of countless fields. From stock market trends to weather patterns, it holds the key to understanding and predicting the future.

Traditionally, unraveling these insights required wading through complex statistical analysis and code. However, a new wave of technology is making waves: Large Language Models (LLMs) are revolutionizing how we analyze time series data, especially with the use of LangChain agents.

In this article, we will navigate the exciting world of LLM-based time series analysis. We will explore how LLMs can be used to unearth hidden patterns in your data, forecast future trends, and answer your most pressing questions about time series data using plain English.


Large language model bootcamp


We will see how to integrate Langchain’s Pandas Agent, a powerful LLM tool, into your existing workflow for seamless exploration. 

Uncover Hidden Trends with LLMs 

LLMs are powerful AI models trained on massive amounts of text data. They excel at understanding and generating human language. But their capabilities extend far beyond just words. Researchers are now unlocking their potential for time series analysis by bridging the gap between numerical data and natural language. 

Here’s how LLMs are transforming the game: 

  • Natural Language Prompts: Imagine asking questions about your data like, “Is there a correlation between ice cream sales and temperature?” LLMs can be prompted in natural language, deciphering your intent, and performing the necessary analysis on the underlying time series data. 
  • Pattern Recognition: LLMs excel at identifying patterns in language. This ability translates to time series data as well. They can uncover hidden trends, periodicities, and seasonality within the data stream. 
  • Uncertainty Quantification: Forecasting the future is inherently uncertain. LLMs can go beyond just providing point predictions. They can estimate the likelihood of different outcomes, giving you a more holistic picture of potential future scenarios.

LLM Applications Across Various Industries 

While LLM-based time series analysis is still evolving, it holds immense potential for various applications: 

  • Financial analysis: Analyze market trends, predict stock prices, and identify potential risks with greater accuracy. 
  • Supply chain management: Forecast demand fluctuations, optimize inventory levels, and prevent stockouts. 
  • Scientific discovery: Uncover hidden patterns in environmental data, predict weather patterns, and accelerate scientific research. 
  • Anomaly detection: Identify unusual spikes or dips in data streams, pinpointing potential equipment failures or fraudulent activities. 


How generative AI and LLMs work


LangChain Pandas Agent 

Lang Chain Pandas Agent is a Python library built on top of the popular Pandas library. It provides a comprehensive set of tools and functions specifically designed for data analysis. The agent simplifies the process of handling, manipulating, and visualizing time series data, making it an ideal choice for both beginners and experienced data analysts. 

It exemplifies the power of LLMs for time series analysis. It acts as a bridge between these powerful language models and the widely used Panda’s library for data manipulation. Users can interact with their data using natural language commands, making complex analysis accessible to a wider audience. 

Key Features 

  • Data Preprocessing: The agent offers various techniques for cleaning and preprocessing time series data, including handling missing values, removing outliers, and normalizing data. 
  • Time-based Indexing: Lang Chain Pandas Agent allows users to easily set time-based indexes, enabling efficient slicing, filtering, and grouping of time series data. 
  • Resampling and Aggregation: The agent provides functions for resampling time series data at different frequencies and aggregating data over specific time intervals. 
  • Visualization: With built-in plotting capabilities, the agent allows users to create insightful visualizations such as line plots, scatter plots, and histograms to analyze time series data. 
  • Statistical Analysis: Lang Chain Pandas Agent offers a wide range of statistical functions to calculate various metrics like mean, median, standard deviation, and more.


Read along to understand sentiment analysis in LLMs


Time Series Analysis with LangChain Pandas Agent 

Using LangChain Pandas Agent, we can perform a variety of time series analysis techniques, including: 

  • Trend Analysis: By applying techniques like moving averages and exponential smoothing, we can identify and analyze trends in time series data. 
  • Seasonality Analysis: The agent provides tools to detect and analyze seasonal patterns within time series data, helping us understand recurring trends. 
  • Forecasting: With the help of advanced forecasting models like ARIMA and SARIMA, Lang Chain Pandas Agent enables us to make predictions based on historical time series data. 

LLMs in Action with LangChain Agents

Suppose you are using LangChain, a popular data analysis platform. LangChain’s Pandas Agent seamlessly integrates LLMs into your existing workflows. Here is how: 

  1. Load your time series data: Simply upload your data into LangChain as you normally would. 
  1. Engage the LLM: Activate LangChain’s Pandas Agent, your LLM-powered co-pilot. 
  1. Ask away: Fire away your questions in plain English. “What factors are most likely to influence next quarter’s sales?” or “Is there a seasonal pattern in customer churn?” The LLM will analyze your data and deliver clear, concise answers. 


Learn to build custom chatbots using LangChain


Now Let’s explore Tesla’s stock performance over the past year and demonstrate how Language Models (LLMs) can be utilized for data analysis and unveil valuable insights into market trends.

To begin, we download the dataset and import it into our code editor using the following snippet:



Dataset Preview

Below are the first five rows of our dataset


LangChain Agents_Data Preview


Next, let’s install and import important libraries from LangChain that are instrumental in data analysis.



Following that, we will create a LangChain Pandas DataFrame agent utilizing OpenAI’s API.


With just these few lines of code executed, your LLM-based agent is now primed to extract valuable insights using simple language commands.

Initial Understanding of Data



Lagchain agents - Initial Understanding of Data - Prompt



The analysis of Tesla’s closing stock prices reveals that the average closing price was $217.16. There was a standard deviation of $37.73, indicating some variation in the daily closing prices. The minimum closing price was $142.05, while the maximum reached $293.34.

This comprehensive overview offers insights into the distribution and fluctuation of Tesla’s stock prices during the period analyzed.



Langchain agents - Initial Understanding of Data - Prompt 2



The daily change in Tesla’s closing stock price is calculated, providing valuable insights into its day-to-day fluctuations. The average daily change, computed at 0.0618, signifies the typical amount by which Tesla’s closing stock price varied over the specified period.

This metric offers investors and analysts a clear understanding of the level of volatility or stability exhibited by Tesla’s stock daily, aiding in informed decision-making and risk assessment strategies.

Detecting Anomalies



Langchain agents - Detecting Anomalies - Prompt



In the realm of anomaly detection within financial data, the absence of outliers in closing prices, as determined by the 1.5*IQR rule, is a notable finding. This suggests that within the dataset under examination, there are no extreme values that significantly deviate from the norm.

However, it is essential to underscore that while this statistical method provides a preliminary assessment, a comprehensive analysis should incorporate additional factors and context to conclusively ascertain the presence or absence of outliers.

This comprehensive approach ensures a more nuanced understanding of the data’s integrity and potential anomalies, thus aiding in informed decision-making processes within the financial domain.

Visualizing Data



Langchain agents - Visualizing Data - Prompt


Langchain agents - Visualizing Data - Graph



The chart above depicts the daily closing price of Tesla’s stock plotted over the past year. The horizontal x-axis represents the dates, while the vertical y-axis shows the corresponding closing prices in USD. Each data point is connected by a line, allowing us to visualize trends and fluctuations in the stock price over time. 

By analyzing this chart, we can identify trends like upward or downward movements in Tesla’s stock price. Additionally, sudden spikes or dips might warrant further investigation into potential news or events impacting the stock market.




Langchain agents - Forecasting - Prompt



Even with historical data, predicting the future is a complex task for Large Language Models. Large language models excel at analyzing information and generating text, they cannot reliably forecast stock prices. The stock market is influenced by many unpredictable factors, making precise predictions beyond historical trends difficult.

The analysis reveals an average price of $217.16 with some variation, but for a more confident prediction of Tesla’s price next month, human experts and consideration of current events are crucial.

Key Findings



Langchain agents - Key Findings - Prompt



The generated natural language summary encapsulates the essential insights gleaned from the data analysis. It underscores the stock’s average price, revealing its range from $142.05 to $293.34. Notably, the analysis highlights the stock’s low volatility, a significant metric for investors gauging risk.

With a standard deviation of $37.73, it paints a picture of stability amidst market fluctuations. Furthermore, the observation that most price changes are minor, averaging just 0.26%, provides valuable context on the stock’s day-to-day movements.

This concise summary distills complex data into digestible nuggets, empowering readers to grasp key findings swiftly and make informed decisions.

Limitations and Considerations 

While LLMs offer significant advantages in time series analysis, it is essential to be aware of its limitations. These include the lack of domain-specific knowledge, sensitivity to input wording, biases in training data, and a limited understanding of context.

Data scientists must validate responses with domain expertise, frame questions carefully, and remain vigilant about biases and errors. 

  • LLMs are most effective as a supplementary tool. They can be an asset for uncovering hidden patterns and providing context, but they should not be the sole basis for decisions, especially in critical areas like finance. 
  • Combining LLMs with traditional time series models can be a powerful approach. This leverages the strengths of both methods – the ability of LLMs to handle complex relationships and the interpretability of traditional models. 

Overall, LLMs offer exciting possibilities for time series analysis, but it is important to be aware of their limitations and use them strategically alongside other tools for the best results.

Best Practices for Using LLMs in Time Series Analysis 

To effectively utilize LLMs like ChatGPT or Langchain in time series analysis, the following best practices are recommended: 

  • Combine LLM’s insights with domain expertise to ensure accuracy and relevance. 
  • Perform consistency checks by asking LMMs multiple variations of the same question. 
  • Verify critical information and predictions with reliable external sources. 
  • Use LLMs iteratively to generate ideas and hypotheses that can be refined with traditional methods. 
  • Implement bias mitigation techniques to reduce the risk of biased responses. 
  • Design clear prompts specifying the task and desired output. 
  • Use a zero-shot approach for simpler tasks, and fine-tune for complex problems. 


Explore a hands-on curriculum that helps you build custom LLM applications!


LLMs: A Powerful Tool for Data Analytics

In summary, Large Language Models (LLMs) represent a significant shift in data analysis, offering an accessible avenue to obtain desired insights and narratives. The examples displayed highlight the power of adept prompting in unlocking valuable interpretations.

However, this is merely the tip of the iceberg. With a deeper grasp of effective prompting strategies, users can unleash a wealth of analyses, comparisons, and visualizations.

Mastering the art of effective prompting allows individuals to navigate their data with the skill of seasoned analysts, all thanks to the transformative influence of LLMs.


May 23, 2024

Feature Engineering is a process of using domain knowledge to extract and transform features from raw data. These features can be used to improve the performance of Machine Learning Algorithms.


Feature Engineering encompasses a diverse array of techniques, including Feature Transformation, Feature Construction, Feature Selection, Feature Scaling, and Feature Extraction, each playing a crucial role in refining and optimizing the representation of data for machine learning tasks. 


In this blog, we will discuss one of the feature transformation techniques called feature scaling with examples and see how it will be the game changer for our machine learning model accuracy. 


Large language model bootcamp


In the world of data science and machine learning, feature transformation plays a crucial role in achieving accurate and reliable results. By manipulating the input features of a dataset, we can enhance their quality, extract meaningful information, and improve the performance of predictive models. Python, with its extensive libraries and tools, offers a streamlined and efficient process for simplifying feature scaling. 


What is feature scaling?


Feature scaling is a crucial step in the feature transformation process that ensures all features are on a similar scale. It is the process that normalizes the range of input columns and makes it useful for further visualization and machine learning model training. The figure below shows a quick representation of feature scaling techniques that we will discuss in this blog.


feature scaling techniques
A visual representation of feature scaling techniques – Source: someka.net


Why feature scaling is important?


Feature scaling is important because of several factors:

  • It improves the machine learning model’s accuracy
  • It enhances the interpretability of data by transforming features on a common scale, without scaling, it is difficult to make comparisons of two features because of scale difference
  • It speeds up the convergence in optimization algorithms like gradient descent algorithms
  • It reduces the computational resources required for training the model
  • For better accuracy, it is essential for the algorithms that rely on distance measures, such as K-nearest neighbors (KNN) and Support Vector Machines (SVM), to be sensitive to feature scales


Now let’s dive into some important methods of feature scaling and see how they impact data understanding and machine learning model performance.




A feature scaling technique is often applied as part of data preparation for machine learning. The goal of normalization is to change the value of numeric columns in the dataset to use a common scale, without distorting differences in the range of values or losing any information.


Min-Max Scaler


The most commonly used normalization technique is min-max scaling, which transforms the features to a specific range, typically between 0 and 1. Scikit-learn has a built-in class available named MinMaxScaler that we can use directly for normalization. It involves subtracting the minimum value and dividing by the range of the feature using this formula.


Blog | Data Science Dojo



Xi is the value we want to normalize.

Xmax is the maximum value of the feature.

Xmin is the minimum value of the feature.


In this transformation, the mean and standard deviation of the feature may behave differently. Our main focus in this normalization is on the minimum and maximum values. Outliers may disrupt our data pattern, so taking care of them is necessary.


Let’s take an example of a wine dataset that contains various ingredients of wine as features. We take two input features: the quantity of alcohol and malic acid and create a scatter plot as shown below.


feature scaling - normalization
Scatter plot from the wine dataset


When we create a scatter plot between alcohol and malic acid quantities, we can see that min-max scaling simply compresses our dataset into the range of zero to one, while keeping the distribution unchanged.


Learn to build LLM applications




Standardization is a feature scaling technique in which values of features are centered around the mean with unit variance. It is also called Z-Score Normalization. It subtracts the mean value of the feature and divides by the standard deviation (σ) of the feature using the formula:


Blog | Data Science Dojo


Here we leverage a dataset on social network ads to gain a practical understanding of the concept. This dataset includes four input features: User ID, Gender, Age, and Salary. Based on this information, it determines whether the user made a purchase or not (where zero indicates not purchased, and one indicates purchased).


The first five rows of the dataset appear as follows:


dataset for standardization
Dataset for the standardization example


In this example, we extract only two input features (Age and Salary) and use them to determine whether the output indicates a purchase or not as shown below.


data for standardization

Standard Scaler


We use Standard-Scaler from the Scikit-learn preprocessing module to standardize the input features for this feature scaling technique. The following code demonstrates this as shown.



We can see how our features look before and after standardization below.


data before and after standardization


Although it appears that the distribution changes after scaling, let’s visualize both distributions through a scatter plot.


visual representation of impact of scaling on data
Visual representation of the impact of scaling on data


So, when we visualize these distributions through plots, we observe that they remain the same as before. This indicates that scaling doesn’t alter the distribution; it simply centers it around the origin.

Now let’s see what happens when we create a density plot between Age and Estimated Salary with and without scaled features as shown below.


density plots for standardization
Graphical representation of data standardization


In the first plot, we can observe that we are unable to visualize the plot effectively and are not able to draw any conclusions or insights between age and estimated salary due to scale differences. However, in the second plot, we can visualize it and discern how age and estimated salary relate to each other.


This illustrates how scaling assists us by placing the features on similar scales. Note that this technique does not have any impact on outliers. So, if an outlier is present in the dataset, it remains as it is even after standardization. Therefore, we need to address outliers separately.


Model’s performance comparison


Now we use the logistic regression technique to predict whether a person will make a purchase after seeing an advertisement and observe how the model behaves with scaled features compared to without scaled features.



Here, we can observe a drastic improvement in our model accuracy when we apply the same algorithm to standardized features. Initially, our model accuracy is around 65.8%, and after standardization, it improves to 86.7% 


When does it matter?


Note that standardization does not always improve your model accuracy; its effectiveness depends on your dataset and the algorithms you are using. However, it can be very effective when you are working with multivariate analysis and similar methods, such as Principal Component Analysis (PCA), Support Vector Machine (SVM), K-means, Gradient Descent, Artificial Neural Networks (ANN), and K-nearest neighbors (KNN).


However, when you are working with algorithms like decision trees, random forest, Gradient Boosting (G-Boost), and (X-Boost), standardization may not have any impact on improving your model accuracy as these algorithms work on different principles and are not affected by differences in feature scales


To sum it up


We have covered standardization and normalization as two methods of feature scaling, including important techniques like Standard Scaler and Min-Max Scaler. These methods play a crucial role in preparing data for machine learning models, ensuring features are on a consistent scale. By standardizing or normalizing data, we enhance model performance and interpretability, paving the way for more accurate predictions and insights.

February 14, 2024