#https://www.kaggle.com/c/facial-keypoints-detection/details/getting-started-with-r #################################

###Variables for downloaded files data.dir <- ' ' train.file <- paste0(data.dir, 'training.csv') test.file <- paste0(data.dir, 'test.csv') #################################

###Load csv -- creates a data.frame matrix where each column can have a different type. d.train <- read.csv(train.file, stringsAsFactors = F) d.test <- read.csv(test.file, stringsAsFactors = F)

###In training.csv, we have 7049 rows, each one with 31 columns. ###The first 30 columns are keypoint locations, which R correctly identified as numbers. ###The last one is a string representation of the image, identified as a string.

###To look at samples of the data, uncomment this line:

head(d.train)

###Let's save the first column as another variable, and remove it from d.train: ###d.train is our dataframe, and we want the column called Image. ###Assigning NULL to a column removes it from the dataframe

im.train <- d.train$Image d.train$Image <- NULL #removes 'image' from the dataframe

im.test <- d.test$Image d.test$Image <- NULL #removes 'image' from the dataframe

################################# #The image is represented as a series of numbers, stored as a string #Convert these strings to integers by splitting them and converting the result to integer

#strsplit splits the string #unlist simplifies its output to a vector of strings #as.integer converts it to a vector of integers. as.integer(unlist(strsplit(im.train[1], " "))) as.integer(unlist(strsplit(im.test[1], " ")))

###Install and activate appropriate libraries ###The tutorial is meant for Linux and OSx, where they use a different library, so: ###Replace all instances of %dopar% with %do%.

install.packages('foreach')

library("foreach", lib.loc="~/R/win-library/3.3")

###implement parallelization im.train <- foreach(im = im.train, .combine=rbind) %do% { as.integer(unlist(strsplit(im, " "))) } im.test <- foreach(im = im.test, .combine=rbind) %do% { as.integer(unlist(strsplit(im, " "))) } #The foreach loop will evaluate the inner command for each row in im.train, and combine the results with rbind (combine by rows). #%do% instructs R to do all evaluations in parallel. #im.train is now a matrix with 7049 rows (one for each image) and 9216 columns (one for each pixel):

###Save all four variables in data.Rd file ###Can reload them at anytime with load('data.Rd')

save(d.train, im.train, d.test, im.test, file='data.Rd')

load('data.Rd')

#each image is a vector of 96*96 pixels (96*96 = 9216). #convert these 9216 integers into a 96x96 matrix: im <- matrix(data=rev(im.train[1,]), nrow=96, ncol=96)

#im.train[1,] returns the first row of im.train, which corresponds to the first training image. #rev reverse the resulting vector to match the interpretation of R's image function #(which expects the origin to be in the lower left corner).

#To visualize the image we use R's image function: image(1:96, 1:96, im, col=gray((0:255)/255))

#Let’s color the coordinates for the eyes and nose points(96-d.train$nose_tip_x[1], 96-d.train$nose_tip_y[1], col="red") points(96-d.train$left_eye_center_x[1], 96-d.train$left_eye_center_y[1], col="blue") points(96-d.train$right_eye_center_x[1], 96-d.train$right_eye_center_y[1], col="green")

#Another good check is to see how variable is our data. #For example, where are the centers of each nose in the 7049 images? (this takes a while to run): for(i in 1:nrow(d.train)) { points(96-d.train$nose_tip_x[i], 96-d.train$nose_tip_y[i], col="red") }

#there are quite a few outliers -- they could be labeling errors. Looking at one extreme example we get this: #In this case there's no labeling error, but this shows that not all faces are centralized idx <- which.max(d.train$nose_tip_x) im <- matrix(data=rev(im.train[idx,]), nrow=96, ncol=96) image(1:96, 1:96, im, col=gray((0:255)/255)) points(96-d.train$nose_tip_x[idx], 96-d.train$nose_tip_y[idx], col="red")

#One of the simplest things to try is to compute the mean of the coordinates of each keypoint in the training set and use that as a prediction for all images colMeans(d.train, na.rm=T)

#To build a submission file we need to apply these computed coordinates to the test instances: p <- matrix(data=colMeans(d.train, na.rm=T), nrow=nrow(d.test), ncol=ncol(d.train), byrow=T) colnames(p) <- names(d.train) predictions <- data.frame(ImageId = 1:nrow(d.test), p) head(predictions)

#The expected submission format has one one keypoint per row, but we can easily get that with the help of the reshape2 library:

install.packages('reshape2')

library(...

Young and older adult vowel categorization responses

https://doi.org/10.5061/dryad.brv15dvh0

On each trial, participants heard a stimulus and clicked a box on the computer screen to indicate whether they heard "SET" or "SAT." Responses of "SET" are coded as 0 and responses of "SAT" are coded as 1. The continuum steps, from 1-7, for duration and spectral quality cues of the stimulus on each trial are named "DurationStep" and "SpectralStep," respectively. Group (young or older adult) and listening condition (quiet or noise) information are provided for each row of the dataset.

📹Project Video available on YouTube - https://youtu.be/WmJYHz_qn5s

🖇️Connect with me on LinkedIn - https://www.linkedin.com/in/rohit-grewal

Realistic Synthetic - AI Financial & Market Data for Gemini(Google), ChatGPT(OpenAI), Llama(Meta)

This dataset provides a synthetic, daily record of financial market activities related to companies involved in Artificial Intelligence (AI). There are key financial metrics and events that could influence a company's stock performance like launch of Llama by Meta, launch of GPT by OpenAI, launch of Gemini by Google etc. Here, we have the data about how much amount the companies are spending on R & D of their AI's Products & Services, and how much revenue these companies are generating. The data is from January 1, 2015, to December 31, 2024, and includes information for various companies : OpenAI, Google and Meta.

This data is available as a CSV file. We are going to analyze this data set using the Pandas DataFrame.

This analyse will be helpful for those working in Finance or Share Market domain.

From this dataset, we extract various insights using Python in our Project.

1) How much amount the companies spent on R & D ?

2) Revenue Earned by the companies

3) Date-wise Impact on the Stock

4) Events when Maximum Stock Impact was observed

5) AI Revenue Growth of the companies

6) Correlation between the columns

7) Expenditure vs Revenue year-by-year

8) Event Impact Analysis

9) Change in the index wrt Year & Company

These are the main Features/Columns available in the dataset :

1) Date: This column indicates the specific calendar day for which the financial and AI-related data is recorded. It allows for time-series analysis of the trends and impacts.

2) Company: This column specifies the name of the company to which the data in that particular row belongs. Examples include "OpenAI" and "Meta".

3) R&D_Spending_USD_Mn: This column represents the Research and Development (R&D) spending of the company, measured in Millions of USD. It serves as an indicator of a company's investment in innovation and future growth, particularly in the AI sector.

4) AI_Revenue_USD_Mn: This column denotes the revenue generated specifically from AI-related products or services, also measured in Millions of USD. This metric highlights the direct financial success derived from AI initiatives.

5) AI_Revenue_Growth_%: This column shows the percentage growth of AI-related revenue for the company on a daily basis. It indicates the pace at which a company's AI business is expanding or contracting.

6) Event: This column captures any significant events or announcements made by the company that could potentially influence its financial performance or market perception. Examples include "Cloud AI launch," "AI partnership deal," "AI ethics policy update," and "AI speech recognition release." These events are crucial for understanding sudden shifts in stock impact.

7) Stock_Impact_%: This column quantifies the percentage change in the company's stock price on a given day, likely in response to the recorded financial metrics or events. It serves as a direct measure of market reaction.

The Russian Financial Statements Database (RFSD) is an open, harmonized collection of annual unconsolidated financial statements of the universe of Russian firms:

• 🔓 First open data set with information on every active firm in Russia.

• 🗂️ First open financial statements data set that includes non-filing firms.

• 🏛️ Sourced from two official data providers: the Rosstat and the Federal Tax Service.

• 📅 Covers 2011-2023 initially, will be continuously updated.

• 🏗️ Restores as much data as possible through non-invasive data imputation, statement articulation, and harmonization.

The RFSD is hosted on 🤗 Hugging Face and Zenodo and is stored in a structured, column-oriented, compressed binary format Apache Parquet with yearly partitioning scheme, enabling end-users to query only variables of interest at scale.

The accompanying paper provides internal and external validation of the data: http://arxiv.org/abs/2501.05841.

Here we present the instructions for importing the data in R or Python environment. Please consult with the project repository for more information: http://github.com/irlcode/RFSD.

Importing The Data

You have two options to ingest the data: download the .parquet files manually from Hugging Face or Zenodo or rely on 🤗 Hugging Face Datasets library.

Python

🤗 Hugging Face Datasets

It is as easy as:

from datasets import load_dataset import polars as pl

This line will download 6.6GB+ of all RFSD data and store it in a 🤗 cache folder

RFSD = load_dataset('irlspbru/RFSD')

Alternatively, this will download ~540MB with all financial statements for 2023# to a Polars DataFrame (requires about 8GB of RAM)

RFSD_2023 = pl.read_parquet('hf://datasets/irlspbru/RFSD/RFSD/year=2023/*.parquet')

Please note that the data is not shuffled within year, meaning that streaming first n rows will not yield a random sample.

Local File Import

Importing in Python requires pyarrow package installed.

import pyarrow.dataset as ds import polars as pl

Read RFSD metadata from local file

RFSD = ds.dataset("local/path/to/RFSD")

Use RFSD_dataset.schema to glimpse the data structure and columns' classes

print(RFSD.schema)

Load full dataset into memory

RFSD_full = pl.from_arrow(RFSD.to_table())

Load only 2019 data into memory

RFSD_2019 = pl.from_arrow(RFSD.to_table(filter=ds.field('year') == 2019))

Load only revenue for firms in 2019, identified by taxpayer id

RFSD_2019_revenue = pl.from_arrow( RFSD.to_table( filter=ds.field('year') == 2019, columns=['inn', 'line_2110'] ) )

Give suggested descriptive names to variables

renaming_df = pl.read_csv('local/path/to/descriptive_names_dict.csv') RFSD_full = RFSD_full.rename({item[0]: item[1] for item in zip(renaming_df['original'], renaming_df['descriptive'])})

R

Local File Import

Importing in R requires arrow package installed.

library(arrow) library(data.table)

Read RFSD metadata from local file

RFSD <- open_dataset("local/path/to/RFSD")

Use schema() to glimpse into the data structure and column classes

schema(RFSD)

Load full dataset into memory

scanner <- Scanner$create(RFSD) RFSD_full <- as.data.table(scanner$ToTable())

Load only 2019 data into memory

scan_builder <- RFSD$NewScan() scan_builder$Filter(Expression$field_ref("year") == 2019) scanner <- scan_builder$Finish() RFSD_2019 <- as.data.table(scanner$ToTable())

Load only revenue for firms in 2019, identified by taxpayer id

scan_builder <- RFSD$NewScan() scan_builder$Filter(Expression$field_ref("year") == 2019) scan_builder$Project(cols = c("inn", "line_2110")) scanner <- scan_builder$Finish() RFSD_2019_revenue <- as.data.table(scanner$ToTable())

Give suggested descriptive names to variables

renaming_dt <- fread("local/path/to/descriptive_names_dict.csv") setnames(RFSD_full, old = renaming_dt$original, new = renaming_dt$descriptive)

Use Cases

🌍 For macroeconomists: Replication of a Bank of Russia study of the cost channel of monetary policy in Russia by Mogiliat et al. (2024) — interest_payments.md

🏭 For IO: Replication of the total factor productivity estimation by Kaukin and Zhemkova (2023) — tfp.md

🗺️ For economic geographers: A novel model-less house-level GDP spatialization that capitalizes on geocoding of firm addresses — spatialization.md

FAQ

Why should I use this data instead of Interfax's SPARK, Moody's Ruslana, or Kontur's Focus?hat is the data period?

To the best of our knowledge, the RFSD is the only open data set with up-to-date financial statements of Russian companies published under a permissive licence. Apart from being free-to-use, the RFSD benefits from data harmonization and error detection procedures unavailable in commercial sources. Finally, the data can be easily ingested in any statistical package with minimal effort.

What is the data period?

We provide financials for Russian firms in 2011-2023. We will add the data for 2024 by July, 2025 (see Version and Update Policy below).

Why are there no data for firm X in year Y?

Although the RFSD strives to be an all-encompassing database of financial statements, end users will encounter data gaps:

We do not include financials for firms that we considered ineligible to submit financial statements to the Rosstat/Federal Tax Service by law: financial, religious, or state organizations (state-owned commercial firms are still in the data).

Eligible firms may enjoy the right not to disclose under certain conditions. For instance, Gazprom did not file in 2022 and we had to impute its 2022 data from 2023 filings. Sibur filed only in 2023, Novatek — in 2020 and 2021. Commercial data providers such as Interfax's SPARK enjoy dedicated access to the Federal Tax Service data and therefore are able source this information elsewhere.

Firm may have submitted its annual statement but, according to the Uniform State Register of Legal Entities (EGRUL), it was not active in this year. We remove those filings.

Why is the geolocation of firm X incorrect?

We use Nominatim to geocode structured addresses of incorporation of legal entities from the EGRUL. There may be errors in the original addresses that prevent us from geocoding firms to a particular house. Gazprom, for instance, is geocoded up to a house level in 2014 and 2021-2023, but only at street level for 2015-2020 due to improper handling of the house number by Nominatim. In that case we have fallen back to street-level geocoding. Additionally, streets in different districts of one city may share identical names. We have ignored those problems in our geocoding and invite your submissions. Finally, address of incorporation may not correspond with plant locations. For instance, Rosneft has 62 field offices in addition to the central office in Moscow. We ignore the location of such offices in our geocoding, but subsidiaries set up as separate legal entities are still geocoded.

Why is the data for firm X different from https://bo.nalog.ru/?

Many firms submit correcting statements after the initial filing. While we have downloaded the data way past the April, 2024 deadline for 2023 filings, firms may have kept submitting the correcting statements. We will capture them in the future releases.

Why is the data for firm X unrealistic?

We provide the source data as is, with minimal changes. Consider a relatively unknown LLC Banknota. It reported 3.7 trillion rubles in revenue in 2023, or 2% of Russia's GDP. This is obviously an outlier firm with unrealistic financials. We manually reviewed the data and flagged such firms for user consideration (variable outlier), keeping the source data intact.

Why is the data for groups of companies different from their IFRS statements?

We should stress that we provide unconsolidated financial statements filed according to the Russian accounting standards, meaning that it would be wrong to infer financials for corporate groups with this data. Gazprom, for instance, had over 800 affiliated entities and to study this corporate group in its entirety it is not enough to consider financials of the parent company.

Why is the data not in CSV?

The data is provided in Apache Parquet format. This is a structured, column-oriented, compressed binary format allowing for conditional subsetting of columns and rows. In other words, you can easily query financials of companies of interest, keeping only variables of interest in memory, greatly reducing data footprint.

Version and Update Policy

Version (SemVer): 1.0.0.

We intend to update the RFSD annualy as the data becomes available, in other words when most of the firms have their statements filed with the Federal Tax Service. The official deadline for filing of previous year statements is April, 1. However, every year a portion of firms either fails to meet the deadline or submits corrections afterwards. Filing continues up to the very end of the year but after the end of April this stream quickly thins out. Nevertheless, there is obviously a trade-off between minimization of data completeness and version availability. We find it a reasonable compromise to query new data in early June, since on average by the end of May 96.7% statements are already filed, including 86.4% of all the correcting filings. We plan to make a new version of RFSD available by July.

Licence

Creative Commons License Attribution 4.0 International (CC BY 4.0).

Copyright © the respective contributors.

Citation

Please cite as:

@unpublished{bondarkov2025rfsd, title={{R}ussian {F}inancial {S}tatements {D}atabase}, author={Bondarkov, Sergey and Ledenev, Victor and Skougarevskiy, Dmitriy}, note={arXiv preprint arXiv:2501.05841}, doi={https://doi.org/10.48550/arXiv.2501.05841}, year={2025}}

Acknowledgments and Contacts

Data collection and processing: Sergey Bondarkov, sbondarkov@eu.spb.ru, Viktor Ledenev, vledenev@eu.spb.ru

Project conception, data validation, and use cases: Dmitriy Skougarevskiy, Ph.D.,

Welcome to my Kickstarter case study! In this project I’m trying to understand what the success’s factors for a Kickstarter campaign are, analyzing an available public dataset from Web Robots. The process of analysis will follow the data analysis roadmap: ASK, PREPARE, PROCESS, ANALYZE, SHARE and ACT.

ASK

Different questions will guide my analysis: 1. Is the campaign duration influencing the success of the project? 2. Is it the chosen funding budget? 3. Which category of campaign is the most likely to be successful?

PREPARE

I’m using the Kickstarter Datasets publicly available on Web Robots. Data are scraped using a bot which collects the data in CSV format once a month and all the data are divided into CSV files. Each table contains: - backers_count : number of people that contributed to the campaign - blurb : a captivating text description of the project - category : the label categorizing the campaign (technology, art, etc) - country - created_at : day and time of campaign creation - deadline : day and time of campaign max end - goal : amount to be collected - launched_at : date and time of campaign launch - name : name of campaign - pledged : amount of money collected - state : success or failure of the campaign

Each month scraping produce a huge amount of CSVs, so for an initial analysis I decided to focus on three months: November and December 2023, and January 2024. I’ve downloaded zipped files which once unzipped contained respectively: 7 CSVs (November 2023), 8 CSVs (December 2023), 8 CSVs (January 2024). Each month was divided into a specific folder.

Having a first look at the spreadsheets, it’s clear that there is some need for cleaning and modification: for example, dates and times are shown in Unix code, there are multiple columns that are not helpful for the scope of my analysis, currencies need to be uniformed (some are US$, some GB£, etc). In general, I have all the data that I need to answer my initial questions, identify trends, and make predictions.

PROCESS

I decided to use R to clean and process the data. For each month I started setting a new working environment in its own folder. After loading the necessary libraries: R library(tidyverse) library(lubridate) library(ggplot2) library(dplyr) library(tidyr) I scripted a general R code that searches for CSVs files in the folder, open them as separate variable and into a single data frame:

csv_files <- list.files(pattern = "\\.csv$")
data_frames <- list()

for (file in csv_files) {
 variable_name <- sub("\\.csv$", "", file)
 assign(variable_name, read.csv(file))
 data_frames[[variable_name]] <- get(variable_name)
}

Next, I converted some columns in numeric values because I was running into types error when trying to merge all the CSVs into a single comprehensive file.

data_frames <- lapply(data_frames, function(df) {
 df$converted_pledged_amount <- as.numeric(df$converted_pledged_amount)
 return(df)
})
data_frames <- lapply(data_frames, function(df) {
 df$usd_exchange_rate <- as.numeric(df$usd_exchange_rate)
 return(df)
})
data_frames <- lapply(data_frames, function(df) {
 df$usd_pledged <- as.numeric(df$usd_pledged)
 return(df)
})

In each folder I then ran a command to merge the CSVs in a single file (one for November 2023, one for December 2023 and one for January 2024):

all_nov_2023 = bind_rows(data_frames)
all_dec_2023 = bind_rows(data_frames)
all_jan_2024 = bind_rows(data_frames)`

After merging I converted the UNIX code datestamp into a readable datetime for the columns “created”, “launched”, “deadline” and deleted all the columns that had these data set to 0. I also filtered the values into the “slug” columns to show only the category of the campaign, without unnecessary information for the scope of my analysis. The final table was then saved.

filtered_dec_2023 <- all_dec_2023 %>% #this was modified according to the considered month
 select(blurb, backers_count, category, country, created_at, launched_at, deadline,currency, usd_exchange_rate, goal, pledged, state) %>%
 filter(created_at != 0 & deadline != 0 & launched_at != 0) %>% 
 mutate(category_slug = sub('.*?"slug":"(.*?)".*', '\\1', category)) %>% 
 mutate(created = as.POSIXct(created_at, origin = "1970-01-01")) %>% 
 mutate(launched = as.POSIXct(launched_at, origin = "1970-01-01")) %>% 
 mutate(setted_deadline = as.POSIXct(deadline, origin = "1970-01-01")) %>% 
 select(-category, -deadline, -launched_at, -created_at) %>% 
 relocate(created, launched, setted_deadline, .before = goal)

write.csv(filtered_dec_2023, "filtered_dec_2023.csv", row.names = FALSE)

The three generated files were then merged into one comprehensive CSV called "kickstarter_cleaned" which was further modified, converting a...

SOURCE

This data was obtained from the Maricopa County Assessor under the search "Fast Food". The query has approximately 1342 results, with only 1000 returned due MCA Data Policies.

DATA CLEANING

Due to some Subdivision Name values posessing unescaped commas that interfered with Pandas' ability to properly align the columns, some manual cleaning in Libre Office was performed by me.

Aside from a handful of Null values, the data is fairly clean and requires little from Pandas.

NULL VALUES

Here are the sums and percentage of NULLS in the dataframe. Interestingly, there are 17 NULLS that do not have any physical addresses. This amounts to 1.7% of values for the Address, City, and Zip, and are all corresponding rows for those missing values.

I have looked into a couple of these on the Maricopa County Assessor's GIS Portal, and they do not appear to have any assigned physical addresses. This is a good avenue of exploration for EDA. Possibly an error that could be corrected, or some obscure legal reason, but interesting nonetheless.

Additionally, there are 391 NULLS in Subdivision Name accounting for 39.1%. This is a feature that I am interested in exploring to determine if there are any predominant groups. It could also generate a list of Entities that can be searched later to see if the dataset can be enriched beyond it's initial 1,000 record limit.

There are 348 NULLS in the MCR column. This is the definition according to the MCA Glossary

MCR (MARICOPA COUNTY RECORDER NUMBER)
Often associated with recorded plat maps.

This seems to be an uninteresting nominal value, so I will drop this columns.

While Property Type and Rental have no NULLS, 100% of those values are Fast Food Restaurant and N (for No), and therefore offer no useful information, and will be dropped.

I will leave the S/T/R column, although it also seems to be uninteresting nominal values, I am curious if there are predominent groups, and since it also has no NULLS, might be useful for further data enrichment.