[ { "database": "sf_food_inspections_lives", "table": "inspection_records", "sql": "CREATE TABLE inspection_records (\n\tbusiness_id INT(11) NOT NULL, \n\tbusiness_name VARCHAR(64) NOT NULL, \n\tbusiness_address VARCHAR(50), \n\tbusiness_city VARCHAR(13) NOT NULL, \n\tbusiness_state VARCHAR(2) NOT NULL, \n\tbusiness_postal_code VARCHAR(9), \n\tbusiness_latitude FLOAT, \n\tbusiness_longitude FLOAT, \n\tbusiness_phone_number BIGINT, \n\tinspection_id VARCHAR(14) NOT NULL, \n\tinspection_date DATE NOT NULL, \n\tinspection_score INT(11), \n\tinspection_type VARCHAR(33) NOT NULL, \n\tviolation_id VARCHAR(21), \n\tviolation_description VARCHAR(73), \n\trisk_category VARCHAR(13)\n)", "col_names": [ "business_id", "business_name", "business_address", "business_city", "business_state", "business_postal_code", "business_latitude", "business_longitude", "business_phone_number", "inspection_id", "inspection_date", "inspection_score", "inspection_type", "violation_id", "violation_description", "risk_category" ], "questions": [ "1. Does business_id have any impact on inspection_score? ", "2. What is the distribution of risk_category for the businesses in California?", "3. What is the most common inspection_type for the businesses in San Francisco?", "4. What is the average inspection_score for businesses in a certain business_postal_code?", "5. Does the percentage of violations increase in certain neighborhoods based on business_latitude and business_longitude?", "6. What is the average inspection_score for businesses with a certain business_phone_number?", "7. Is there any correlation between different violation_id and the inspection_score?", "8. What is the distribution of violations with respect to inspection_type?", "9. Does business_state have an impact on risk_category?", "10. What is the most commonly violated inspection_type in business_city?", "11. Are there any patterns in the average inspection_score with respect to inspection_date?", "12. Are businesses with a certain business_address more likely to receive violations with a risk_category 'High'?", "13. What is the average inspection_score difference between businesses in different business_states?", "14. How often do violation_descriptions occur with respect to the business_name?", "15. How does the number of inspection_score change from one violation_id to the next?", "16. Is there a difference in inspection_type between businesses that have similar business_phone_number?", "17. Are there any patterns in the risk_category for violation_descriptions?", "18. What percentage of businesses located in a certain business_city have been inspected in the last year?", "19. What is the most common violation_id for businesses located in business_state?", "20. Are businesses in certain business_postal_codes more likely to receive a high inspection_score?" ] }, { "database": "florida_deathrow", "table": "inmates", "sql": "CREATE TABLE \"inmates\" (\n\t`Inmate Name`\tTEXT NOT NULL,\n\t`DC#`\tTEXT NOT NULL,\n\t`Race/Gender`\tTEXT NOT NULL,\n\t`Date Received`\tDATE NOT NULL,\n\t`Crime`\tTEXT NOT NULL,\n\t`Date of Offense`\tDATE NOT NULL,\n\t`Date of Sentence`\tDATE NOT NULL,\n\t`Date of Birth`\tDATE NOT NULL,\n\t`County`\tTEXT NOT NULL\n)", "col_names": [ "Inmate Name", "DC#", "Race/Gender", "Date Received", "Crime", "Date of Offense", "Date of Sentence", "Date of Birth", "County" ], "questions": [ "1. How many inmates are in total in Florida Deathrow?", "2. What is the average age of all the inmates in Florida Deathrow?", "3. What is the most common race/gender in Florida Deathrow?", "4. What is the most common crime among inmates in Florida Deathrow?", "5. How many inmates are on death row in each individual county in Florida?", "6. Over how long a period of time were inmates received in Florida Deathrow?", "7. How many inmates have committed crimes within two years of receiving their sentence?", "8. Which counties have the most inmates on death row?", "9. What is the average length of time between the date of offense and the date of sentence among inmates in Florida Deathrow?", "10. What is the variance in sentence dates between different races/genders in Florida Deathrow?", "11. How has the number of inmates sentenced to death row changed over time?", "12. How does the average age of the inmates on Florida Deathrow vary by county?", "13. What percentage of inmates on Florida Deathrow are convicted of first-degree murders?", "14. What is the most common type of offense in Florida Deathrow?", "15. How many inmates sentenced to death row were under the age of 18 at the time of the offense?", "16. How has sentencing of inmates to death row changed since 1990?", "17. How many inmates in Florida Deathrow have been on death row for more than 10 years?", "18. What is the average age at the time of offense for inmates on death row in Florida?", "19. What is the distribution of time served on death row among inmates in Florida?", "20. What is the average time between the date of sentencing and birth for inmates in Florida Deathrow?" ] }, { "database": "sfscores", "table": "businesses", "sql": "CREATE TABLE businesses (\n\tbusiness_id INT(11) NOT NULL, \n\tname VARCHAR(64), \n\taddress VARCHAR(50), \n\tcity VARCHAR(23), \n\tpostal_code VARCHAR(9), \n\tlatitude FLOAT, \n\tlongitude FLOAT, \n\tphone_number BIGINT, \n\t\"TaxCode\" VARCHAR(4), \n\tbusiness_certificate INT(11), \n\tapplication_date DATE, \n\towner_name VARCHAR(99), \n\towner_address VARCHAR(74), \n\towner_city VARCHAR(22), \n\towner_state VARCHAR(14), \n\towner_zip VARCHAR(15)\n)", "col_names": [ "business_id", "name", "address", "city", "postal_code", "latitude", "longitude", "phone_number", "TaxCode", "business_certificate", "application_date", "owner_name", "owner_address", "owner_city", "owner_state", "owner_zip" ], "questions": [ "1. What is the total number of businesses in the database?", "2. What is the distribution of businesses across cities?", "3. What is the average latitude and longitude of all businesses?", "4. What is the most common TaxCode among businesses?", "5. What is the median phone number of businesses?", "6. What are the average days between the business certificate application and approval?", "7. What is the most common address among the businesses?", "8. How many businesses are owned by the same person?", "9. What is the most popular business name?", "10. How many businesses are in a particular city?", "11. What is the percentage of businesses with application dates in the year 2021?", "12. How many unique business certificates are available?", "13. What is the most common owner address?", "14. What is the average difference between the owner address and the business address?", "15. How many businesses have the same business and owner name?", "16. What is the Postal Code with the most businesses?", "17. Are there any businesses in the same location with the same address?", "18. What is the most frequent owner state?", "19. What is the median difference between the business and owner zip code?", "20. How many businesses have a phone number in the database?" ] }, { "database": "sfscores", "table": "inspections", "sql": "CREATE TABLE \"inspections\" (\n\t`business_id`\tTEXT NOT NULL,\n\t`Score`\tINT(11),\n\t`date`\tTEXT NOT NULL,\n\t`type`\tVARCHAR(33) NOT NULL\n)", "col_names": [ "business_id", "Score", "date", "type" ], "questions": [ "1. What is the average Score received by the businesses in the sfscores.inspections table?", "2. How many unique businesses are represented in the sfscores.inspections table?", "3. What is the distribution of Scores across different types of businesses in the sfscores.inspections table?", "4. Are there any temporal trends in the Scores given to businesses in the sfscores.inspections table?", "5. What is the highest and lowest Score given to businesses in the sfscores.inspections table?", "6. How many different types of businesses are represented in the sfscores.inspections table?", "7. Are there any businesses with the same Score but different types in the sfscores.inspections table?", "8. Are there any seasonal trends in the Scores given to businesses in the sfscores.inspections table?", "9. Is there a correlation between the types of businesses and the Scores they receive in the sfscores.inspections table?", "10. How does the frequency of inspections performed on different businesses in the sfscores.inspections table vary?", "11. How many unique Scores can be found in the sfscores.inspections table?", "12. Is there a difference in Scores given to businesses in the same type in the sfscores.inspections table?", "13. How many inspections are carried out on each business in the sfscores.inspections table?", "14. Are there any businesses that consistently score better than others in the sfscores.inspections table?", "15. How often are businesses inspected in the sfscores.inspections table?", "16. What is the average Score for businesses inspected on different dates in the sfscores.inspections table?", "17. How many different types of businesses in the sfscores.inspections table receive a Score of 10?", "18. What is the distribution of Scores by different types of businesses in the sfscores.inspections table?", "19. What is the spread of Scores across different business types in the sfscores.inspections table?", "20. Do different types of businesses have similar average Scores in the sfscores.inspections table?" ] }, { "database": "sfscores", "table": "violations", "sql": "CREATE TABLE \"violations\" (\n\t`business_id`\tTEXT NOT NULL,\n\t`date`\tTEXT NOT NULL,\n\t`ViolationTypeID`\tTEXT NOT NULL,\n\t`risk_category`\tTEXT NOT NULL,\n\t`description`\tTEXT NOT NULL\n)", "col_names": [ "business_id", "date", "ViolationTypeID", "risk_category", "description" ], "questions": [ "1. What are the most commonly violated regulations for businesses with business_id?", "2. Can we identify any correlations between ViolationTypeID and risk_category?", "3. Are there certain ViolationTypeIDs that are associated with more severe risk categories?", "4. What is the time distribution of violations across businesses?", "5. Are there certain businesses that have more violations than others?", "6. What is the frequency of violations by ViolationTypeID?", "7. Which risk categories have the highest rate of reported violations?", "8. Are there any geographic trends for violation types?", "9. Are there certain days of the week with more violations?", "10. Are the violations clustered in certain months?", "11. Are there any factors that contribute to the risk category classification of each violation?", "12. Are the most serious violations reported more frequently?", "13. What is the frequency of violations within the last 6 months?", "14. Do the descriptions of violations provide any insight into how regulations are broken?", "15. Does the risk category of a violation impact the amount of time it takes to resolve the violation?", "16. Are the descriptions of the violations related to the types of regulations that are violated?", "17. Do different businesses exhibit different behavior when it comes to the violations that are reported?", "18. Is there a relationship between the type of violation and the seriousness of the violation?", "19. How does the frequency of reported violations vary from business to business?", "20. Are there any underlying patterns in the date, time, type of violation, and risk category of reported violations?" ] }, { "database": "thr_gendered_babynames", "table": "gendered_names", "sql": "CREATE TABLE `gendered_names` (\n `year` INT(11) NOT NULL,\n `state` TEXT NOT NULL,\n `name` TEXT NOT NULL,\n `total_babies` INT(11) NOT NULL,\n `primary_sex` TEXT NOT NULL,\n `primary_sex_ratio` INT(11) NOT NULL,\n `per_100k_in_state` INT(11) NOT NULL\n)", "col_names": [ "year", "state", "name", "total_babies", "primary_sex", "primary_sex_ratio", "per_100k_in_state" ], "questions": [ "1. How has the number of babies given a particular name changed over time in each state?", "2. How are the primary sex ratios for babies with certain names distributed in each state?", "3. Who are the babies with the most popular names in each state in a given year?", "4. Is there a trend in the ratio of boys and girls born over time in each state?", "5. What is the most popular name given to babies in each state in the last 5 years?", "6. Is there a relationship between the total number of babies born and their primary sex in each state?", "7. How is the number of babies given a particular name related to the population of the particular state?", "8. Which states have the highest and lowest primary sex ratios for each gendered name?", "9. Which state has experienced the greatest increase in the total number of babies given a particular name in the last 10 years?", "10. What is the relationship between the primary sex ratio for each name and the population density of the state?", "11. How do state rankings for gendered names for babies change over time?", "12. How does the number of babies with a particular name in each state compare to the national average?", "13. Is there a correlation between the number of babies born in a given year and the total number of babies given a particular name in each state in that year?", "14. Is there a significant difference in the primary sex ratio of babies given a particular name in each state over time?", "15. How has the popularity of particular gendered names changed in each state in the last 5 years?", "16. What are the most and least popular primary sex ratios for babies with a particular name in each state?", "17. How is the ratio of boys and girls born in each state in a given year related to the primary sex ratio of babies given a particular name?", "18. How have the primary sex ratios of babies with a particular name changed over time in each state?", "19. How does the percentage of babies with a particular name compared to the total population of each state changes over time?", "20. Is there a regional or national pattern for the selection of gendered names for babies over time?" ] }, { "database": "thr_gendered_babynames", "table": "thr_power_list", "sql": "CREATE TABLE \"thr_power_list\" (\n\t`rank`\tINT(11),\n\t`full_name`\tTEXT,\n\t`first_name`\tTEXT,\n\t`last_name`\tTEXT,\n\t`occupation`\tTEXT,\n\t`company`\tTEXT\n)", "col_names": [ "rank", "full_name", "first_name", "last_name", "occupation", "company" ], "questions": [ "1.What is the highest ranked first name and last name in the thr_gendered_babynames.thr_power_list table?", "2.What is the most common occupation in the thr_gendered_babynames.thr_power_list table?", "3.Does the rank of the people in the thr_gendered_babynames.thr_power_list table vary by gender? ", "4.Which occupation has the most people in the top ten places of the thr_gendered_babynames.thr_power_list table?", "5.Which companies have the highest number of representatives in the thr_gendered_babynames.thr_power_list table?", "6.What is the percentile rank of individuals with particular occupations?", "7.What is the average rank of people with different occupations in the thr_gendered_babynames.thr_power_list table?", "8.How has the balance of power shifted in the thr_gendered_babynames.thr_power_list table since the last release?", "9.What is the greatest difference in the rank between a first name and last name?", "10.How have the most popular first names changed over time in the thr_gendered_babynames.thr_power_list table?", "11.What is the correlation between first name, last name, and occupation in the thr_gendered_babynames.thr_power_list table?", "12.Which companies have the highest percentage of representation in the thr_gendered_babynames.thr_power_list table?", "13.What is the gender distribution of those working in particular occupations in the thr_gendered_babynames.thr_power_list table?", "14.Which first names are most correlated with particular occupations in the thr_gendered_babynames.thr_power_list table?", "15.What is the relationship between rank and number of first and last names in the thr_gendered_babynames.thr_power_list table?", "16.Are Full names more commonly associated with a particular occupation than just first or last names in the thr_gendered_babynames.thr_power_list table?", "17.What is the most common occupation for individuals with specific first and last names?", "18.Has the percentage of individuals with a particular occupation increased or decreased over time in the thr_gendered_babynames.thr_power_list table?", "19.Which companies are most represented in the top ten most powerful positions in the thr_gendered_babynames.thr_power_list table?", "20.What is the relationship between company, occupation and rank in the thr_gendered_babynames.thr_power_list table?" ] }, { "database": "peninsula_publicpay", "table": "salaries", "sql": "CREATE TABLE \"salaries\" (\n\t`Year`\tINT(11),\n\t`Entity Type`\tTEXT,\n\t`Entity Name`\tTEXT,\n\t`Department / Subdivision`\tTEXT,\n\t`Position`\tTEXT,\n\t`Elected Official`\tBOOLEAN,\n\t`Judicial`\tBOOLEAN,\n\t`Other Positions`\tTEXT,\n\t`Min Classification Salary`\tFLOAT,\n\t`Max Classification Salary`\tFLOAT,\n\t`Reported Base Wage`\tINT(11),\n\t`Regular Pay`\tFLOAT,\n\t`Overtime Pay`\tFLOAT,\n\t`Lump-Sum Pay`\tFLOAT,\n\t`Other Pay`\tFLOAT,\n\t`Total Wages`\tFLOAT,\n\t`Defined Benefit Plan`\tFLOAT,\n\t`Employees Retirement Cost Covered`\tFLOAT,\n\t`Deferred Compensation Plan`\tFLOAT,\n\t`Health Dental Vision`\tFLOAT,\n\t`Total Retirement and Health Cost`\tFLOAT,\n\t`Pension Formula`\tTEXT,\n\t`Entity Population`\tINT(11),\n\t`Entity County`\tTEXT\n)", "col_names": [ "Year", "Entity Type", "Entity Name", "Department / Subdivision", "Position", "Elected Official", "Judicial", "Other Positions", "Min Classification Salary", "Max Classification Salary", "Reported Base Wage", "Regular Pay", "Overtime Pay", "Lump-Sum Pay", "Other Pay", "Total Wages", "Defined Benefit Plan", "Employees Retirement Cost Covered", "Deferred Compensation Plan", "Health Dental Vision", "Total Retirement and Health Cost", "Pension Formula", "Entity Population", "Entity County" ], "questions": [ "1. What is the average reported base wage for Judicial positions across all years?", "2. How many entities are covered in the peninsula_publicpay.salaries table?", "3. What is the highest and lowest total wages recorded in the peninsula_publicpay.salaries table?", "4. How has the number of entities of each entity type changed over the years?", "5. What percentage of entities have employees that are covered by a retirement cost?", "6. What is the average total retirement and health costs per entity?", "7. For which position is the difference between min and max classification salary the highest?", "8. How many employees have deferred compensation plans?", "9. How much has the total lump-sum pay increased over the years?", "10. What are the most common pension formulas across all entities included in the peninsula_publicpay.salaries table?", "11. What is the average reported base wage for elected officials across all years?", "12. How has the number of entities of each entity type changed over the counties in the peninsula_publicpay.salaries table?", "13. What is the most common department for all entities across all years?", "14. How does the average reported base wage differ by position type across all years?", "15. What is the average regular pay for entities in each county?", "16. What is the average overtime pay for entities in each county?", "17. What is the average total wages for entities in each county?", "18. What percentage of entities offer a defined benefit plan?", "19. How much has the total other pay increased over the years?", "20. What is the average entity population of entities included in the peninsula_publicpay.salaries table?" ] }, { "database": "usgs_lower_us", "table": "quakes", "sql": "CREATE TABLE quakes (\n time DATETIME , \n latitude FLOAT , \n longitude FLOAT , \n depth FLOAT , \n mag FLOAT , \n \"magType\" TEXT, \n nst INT(11), \n gap FLOAT, \n dmin FLOAT, \n rms FLOAT, \n net TEXT , \n id TEXT , \n updated DATETIME , \n place TEXT , \n type TEXT , \n \"horizontalError\" FLOAT, \n \"depthError\" FLOAT, \n \"magError\" FLOAT, \n \"magNst\" INT(11), \n status TEXT , \n \"locationSource\" TEXT , \n \"magSource\" TEXT \n)", "col_names": [ "time", "latitude", "longitude", "depth", "mag", "magType", "nst", "gap", "dmin", "rms", "net", "id", "updated", "place", "type", "horizontalError", "depthError", "magError", "magNst", "status", "locationSource", "magSource" ], "questions": [ "1. What is the maximum depth for earthquakes recorded by USGS in the lower US?", "2. How many earthquakes of magnitude 7.0 or higher have been recorded in the lower US?", "3. What is the average magnitude of earthquakes recorded in the last two years in the lower US?", "4. How many earthquakes occurred in the lower US within a 50 mile radius of a given location?", "5. In what locations have earthquakes of magnitude 7.0 or higher occurred in the lower US?", "6. How many earthquakes of magnitude 6.0 or higher have occurred in the lower US since the last major earthquake?", "7. What is the average depth for earthquakes of magnitude 7.0 or higher recorded in the lower US?", "8. How does the average depth of earthquakes in the lower US compare to the global average depth?", "9. What is the average horizontal error for earthquakes recorded in the lower US?", "10. How many earthquakes of magnitude 5.0 or higher have occurred in the lower US since the start of 2017?", "11. What is the average magNST of earthquakes with magnitude 7.0 or higher recorded in the lower US?", "12. How does the average magError of earthquakes in the lower US compare to the global average magError?", "13. What is the maximum magError for earthquakes recorded by USGS in the lower US?", "14. How many earthquakes with a given status have occurred in the lower US?", "15. What is the distribution of location sources for earthquakes with a magnitude 6.0 or higher recorded in the lower US?", "16. How does the average magSource of earthquakes in the lower US compare to other countries?", "17. What is the maximum depthError for earthquakes recorded by USGS in the lower US?", "18. How many earthquakes have occurred in a given time period in the lower US?", "19. What is the average rms of earthquakes recorded in the lower US?", "20. How does the average dmin of earthquakes in the lower US compare to the global average dmin?" ] }, { "database": "simplefolks", "table": "homes", "sql": "CREATE TABLE \"homes\" (\n\t`owner_name`\tTEXT NOT NULL,\n\t`area`\tTEXT NOT NULL,\n\t`value`\tINT(11) NOT NULL\n)", "col_names": [ "owner_name", "area", "value" ], "questions": [ "1. Who is the highest value homeowner in the simplefolks.homes table?", "2. What is the average value of homes in the simplefolks.homes table?", "3. How many homes are owned by owners with the same name in the simplefolks.homes table?", "4. How much area do homes in the simplefolks.homes table occupy on average?", "5. How many homes with an area of more than 1 million square feet are owned by the same owner in the simplefolks.homes table?", "6. What is the total value of all homes in the simplefolks.homes table?", "7. What is the percentage of homeowners with an area of more than 1 million square feet in the simplefolks.homes table?", "8. What is the average value of the homes owned by the same owner in the simplefolks.homes table?", "9. How many distinct homes are in the simplefolks.homes table?", "10. What is the minimum area for a home in the simplefolks.homes table?", "11. What is the maximum value of a home in the simplefolks.homes table?", "12. How many homes with a value below $100,000 are owned by the same owner in the simplefolks.homes table?", "13. What is the average area of homes owned by the same owner in the simplefolks.homes table?", "14. How many of the homes in the simplefolks.homes table have an area above 1 million square feet?", "15. What percent of the homes in the simplefolks.homes table have a value above $1,000,000?", "16. What is the median value of homes in the simplefolks.homes table?", "17. What is the minimum value of homes owned by the same owner in the simplefolks.homes table?", "18. How many homes with a value of more than $1,000,000 are in the simplefolks.homes table?", "19. What is the maximum area for a home in the simplefolks.homes table?", "20. What is the average value of homes with an area of more than 1 million square feet in the simplefolks.homes table?" ] }, { "database": "simplefolks", "table": "people", "sql": "CREATE TABLE \"people\" (\n\t`name`\tTEXT NOT NULL,\n\t`sex`\tTEXT NOT NULL,\n\t`age`\tINT(11) NOT NULL\n)", "col_names": [ "name", "sex", "age" ], "questions": [ "1. What is the average age of people in the \"simplefolks.people\" database?", "2. How many males are there in the \"simplefolks.people\" database?", "3. How many females are there in the \"simplefolks.people\" database?", "4. What is the oldest age recorded in the \"simplefolks.people\" database?", "5. What is the youngest age recorded in the \"simplefolks.people\" database?", "6. What is the most common age in the \"simplefolks.people\" database?", "7. Are there any people of age 0 in the \"simplefolks.people\" database?", "8. What is the average age of males in the \"simplefolks.people\" database?", "9. What is the average age of females in the \"simplefolks.people\" database?", "10. What is the median age of people in the \"simplefolks.people\" database?", "11. Are there any people of age 99 in the \"simplefolks.people\" database?", "12. What is the age range of people in the \"simplefolks.people\" database?", "13. What is the percentage of males in the \"simplefolks.people\" database?", "14. What is the percentage of females in the \"simplefolks.people\" database?", "15. Are there any duplicate names in the \"simplefolks.people\" database?", "16. Is the age distribution in the \"simplefolks.people\" database normal?", "17. What age group has the highest number of people in the \"simplefolks.people\" database?", "18. Do people's names in the \"simplefolks.people\" database correspond to their genders?", "19. Is the age distribution in the \"simplefolks.people\" database uniform?", "20. Are there any people with no gender specified in the \"simplefolks.people\" database?" ] }, { "database": "simplefolks", "table": "pets", "sql": "CREATE TABLE \"pets\" (\n\t`name`\tTEXT NOT NULL,\n\t`type`\tTEXT NOT NULL,\n\t`owner_name`\tTEXT NOT NULL\n)", "col_names": [ "name", "type", "owner_name" ], "questions": [ "1. What is the most common pet type owned by a ‘simplefolks’ person? ", "2. How many people in ‘simplefolks’ own dogs? ", "3. Do people in ‘simplefolks’ tend to have more cats than dogs? ", "4. What is the median pet type owned by ‘simplefolks’ people? ", "5. What is the average number of pets owned by people in ‘simplefolks’? ", "6. How many cat owners are there in ‘simplefolks’? ", "7. Are there more bird owners or fish owners in ‘simplefolks’? ", "8. What percentage of people in ‘simplefolks’ do not own a pet? ", "9. What is the distribution of pet types among ‘simplefolks’ people? ", "10. What is the most popular pet name choice for ‘simplefolks’ people? ", "11. How many unique pet types are owned by ‘simplefolks’ people? ", "12. Are there more people who own multiple pets or single pets in ‘simplefolks’? ", "13. How many people in ‘simplefolks’ own exotic pets? ", "14. Are pet owners in ‘simplefolks’ more likely to have different pet types than pet owners in other communities? ", "15. Are there differences in pet ownership within ‘simplefolks’ based on age, gender, or race? ", "16. Does the number of pets owned by ‘simplefolks’ people vary based on where they live? ", "17. Is there a correlation between pet type and income among ‘simplefolks’ people? ", "18. How does pet ownership in ‘simplefolks’ compare with pet ownership in other communities? ", "19. Do people in ‘simplefolks’ tend to own multiple pets of the same type? ", "20. Is there a certain type of pet that is more popular among ‘simplefolks’ people that is not popular in other communities?" ] }, { "database": "simplefolks", "table": "inmates", "sql": "CREATE TABLE \"inmates\" (\n\t`id`\tTEXT,\n\t`first_name`\tTEXT,\n\t`last_name`\tTEXT,\n\t`birth_year`\tINT(11),\n\t`sentence_start`\tINT(11),\n\t`sentence_end`\tINT(11)\n)", "col_names": [ "id", "first_name", "last_name", "birth_year", "sentence_start", "sentence_end" ], "questions": [ "1. What is the maximum sentence length for inmates?", "2. Who are the oldest living inmates?", "3. What are the most common first and last names among inmates?", "4. How many inmates have been sentenced in the last 10 years?", "5. Is there a correlation between sentence length and birth year?", "6. Are there any inmates whose sentences began and ended in the same year?", "7. How many inmates have birthdays in the month of May?", "8. What is the average sentence length among inmates?", "9. How many inmates were born in the same year as their sentencing date?", "10.What is the longest ongoing sentence among inmates?", "11.What percentage of inmates are over the age of 60?", "12.What are the top three most common birth years among inmates?", "13.How many inmates were born before 1950?", "14.Are any inmates born in the same year their sentence began?", "15.Is there a pattern in the sentence end dates for inmates who started serving a sentence in the same year?", "16.What is the average first name length among inmates?", "17.What is the most common sentence range among inmates?", "18.Are there any inmates with identical birth years and sentence start years?", "19.Are there any inmates whose sentence ended before their birth year?", "20.What is the average sentence length for inmates who began their sentences before 1980?" ] }, { "database": "simplefolks", "table": "politicians", "sql": "CREATE TABLE \"politicians\" (\n\t`bioguide_id`\tTEXT,\n\t`position`\tTEXT,\n\t`state`\tTEXT,\n\t`party`\tTEXT,\n\t`first_name`\tTEXT,\n\t`last_name`\tTEXT,\n\t`birth_year`\tINT(11),\n\t`service_start`\tINT(11),\n\t`service_end`\tINT(11)\n)", "col_names": [ "bioguide_id", "position", "state", "party", "first_name", "last_name", "birth_year", "service_start", "service_end" ], "questions": [ "1. How many politicians from different states are currently in the simplefolks.politicians table?", "2. How many politicians of different parties are currently in the simplefolks.politicians table?", "3. How many politicians of a certain position are currently in the simplefolks.politicians table?", "4. What is the oldest birth year of a politician currently in the simplefolks.politicians table?", "5. What is the most recent birth year of a politician currently in the simplefolks.politicians table?", "6. What are the average service start and end dates of politicians currently in the simplefolks.politicians table?", "7. Who is serving the longest tenure in the simplefolks.politicians table?", "8. What is the average tenure of politicians currently in the simplefolks.politicians table?", "9. Who is the youngest politician currently in the simplefolks.politicians table? ", "10. How many politicians have served in multiple positions?", "11. How many politicians have served in one position only?", "12. Who were the first two politicians to first use the bioguide_id field?", "13. Does the state of residence affect the average tenure of politicians currently in the simplefolks.politicians table?", "14. Are there any unrepresented political parties in the simplefolks.politicians table?", "15. What percentage of politicians have served over 10 years? ", "16. What is the average age of politicians currently in the simplefolks.politicians table?", "17. How many politicians have only served in their current position? ", "18. What is the longest period a politician has served in the simplefolks.politicians table? ", "19. Are there any interesting trends in the service start and end dates of politicians in the simplefolks.politicians table? ", "20. Who are the longest-serving politicians from each US state?" ] }, { "database": "ssa_babynames_nationwide_since_1980", "table": "babynames", "sql": "CREATE TABLE \"babynames\" (\n\t`year`\tINT(11) NOT NULL,\n\t`name`\tTEXT,\n\t`sex`\tTEXT NOT NULL,\n\t`count`\tINT(11) NOT NULL,\n\t`rank_within_sex`\tINT(11) NOT NULL,\n\t`per_100k_within_sex`\tFLOAT NOT NULL\n)", "col_names": [ "year", "name", "sex", "count", "rank_within_sex", "per_100k_within_sex" ], "questions": [ "1. What were the most popular baby names for each given year from 1980 to present? ", "2. What were the most common baby names for each sex in 2019?", "3. How much has the population of babies with each name changed between 1980 and 2020?", "4. What is the average ranking of baby names for each given year?", "5. What are the top 5 names for boys and girls in each year since 1980?", "6. What is the five-year average of the per_100k_within_sex numbers for each name?", "7. How have the names that ended up in the top 10 most popular list changed since 1980? ", "8. What are the most popular name combinations since 1980?", "9. How has the gender gap changed since 1980 in terms of the number of children given a particular name?", "10. How have the rankings of the most popular names in each year changed over time?", "11. What were the top 5 percent of names for each sex in 2020?", "12. How many names have entered the top 10 rankings since 1980?", "13. What has been the average trend of the rank_within_sex for each name since 1980? ", "14. How does the proportion of each name per 100k change year to year? ", "15. How many names had a count of 0 for each year since 1980?", "16. What were the names with the highest counts each year since 1980?", "17. What has been the most common rank within sex for each name from 1980 to 2020? ", "18. How many names have been in the top 5 ranks over the past 40 years?", "19. Is there a correlation between the name’s count and per_100k_within_sex?", "20. What are the most popular names since 1980 that are still increasing in popularity today?" ] }, { "database": "ssa_babynames_for_2015", "table": "babynames", "sql": "CREATE TABLE `babynames` (\n `state` TEXT NOT NULL,\n `year` INT(11) NOT NULL,\n `name` TEXT NOT NULL,\n `sex` TEXT NOT NULL,\n `count` INT(11) NOT NULL,\n `rank_within_sex` INT(11) NOT NULL,\n `per_100k_within_sex` FLOAT NOT NULL\n)", "col_names": [ "state", "year", "name", "sex", "count", "rank_within_sex", "per_100k_within_sex" ], "questions": [ "1. What was the most popular baby name in each state in 2015?", "2. What is the average number of births of each sex in a given year?", "3. What states have the highest rate of baby name registrations in relation to their populations?", "4. Which female name had the most registrations in 2015?", "5. What are the most-used names by male babies?", "6. What was the most popular name among all newborns in 2015?", "7. How many babies were named the same name in each state in 2015?", "8. What are the top 10 most common male and female names in each state in 2015?", "9. What is the standard deviation for the number of births of each sex in a given year?", "10. What is the difference in popularity of baby names between 2015 and 2016?", "11. What is the trend in baby name registrations in each state from 2010 to 2015?", "12. How has the distribution of names changed over the past five years for each sex?", "13. How does the rank of a particular name in a given year compare to its rank within the same sex in other years?", "14. Does the amount of babies born with a certain name have any correlation with its popularity that year? ", "15. How many babies are named the same name in the USA compared to in the state of California?", "16. How many babies of each sex are born each year in each state?", "17. What is the difference in the number of registrations of a certain name in different states?", "18. Is there a significant correlation between the popularity of a name in a certain year and the rank of that name in that same year?", "19. Does the amount of different names registered to newborns in a certain year vary between states?", "20. Does the amount of babies born with a particular name correlate with its rank each year?" ] }, { "database": "cdeschools", "table": "schools", "sql": "CREATE TABLE schools (\n\t\"CDSCode\" VARCHAR(14) NOT NULL, \n\t\"NCESDist\" VARCHAR(7), \n\t\"NCESSchool\" VARCHAR(5), \n\t\"StatusType\" VARCHAR(7) NOT NULL, \n\t\"County\" VARCHAR(15) NOT NULL, \n\t\"District\" VARCHAR(74) NOT NULL, \n\t\"School\" VARCHAR(89), \n\t\"Street\" VARCHAR(62), \n\t\"StreetAbr\" VARCHAR(59), \n\t\"City\" VARCHAR(25), \n\t\"Zip\" VARCHAR(10), \n\t\"State\" VARCHAR(4), \n\t\"MailStreet\" VARCHAR(70), \n\t\"MailStrAbr\" VARCHAR(70), \n\t\"MailCity\" VARCHAR(22), \n\t\"MailZip\" VARCHAR(10), \n\t\"MailState\" VARCHAR(4), \n\t\"Phone\" VARCHAR(14), \n\t\"Ext\" VARCHAR(6), \n\t\"Website\" VARCHAR(96), \n\t\"OpenDate\" DATE, \n\t\"ClosedDate\" DATE, \n\t\"Charter\" BOOLEAN, \n\t\"CharterNum\" VARCHAR(4), \n\t\"FundingType\" VARCHAR(23), \n\t\"DOC\" VARCHAR(2) NOT NULL, \n\t\"DOCType\" VARCHAR(42) NOT NULL, \n\t\"SOC\" VARCHAR(4), \n\t\"SOCType\" VARCHAR(41), \n\t\"EdOpsCode\" VARCHAR(7), \n\t\"EdOpsName\" VARCHAR(43), \n\t\"EILCode\" VARCHAR(8), \n\t\"EILName\" VARCHAR(31), \n\t\"GSoffered\" VARCHAR(16), \n\t\"GSserved\" VARCHAR(5), \n\t\"Virtual\" VARCHAR(4), \n\t\"Magnet\" BOOLEAN, \n\t\"Latitude\" FLOAT, \n\t\"Longitude\" FLOAT, \n\t\"AdmFName1\" VARCHAR(17), \n\t\"AdmLName1\" VARCHAR(22), \n\t\"AdmEmail1\" VARCHAR(49), \n\t\"AdmFName2\" VARCHAR(15), \n\t\"AdmLName2\" VARCHAR(18), \n\t\"AdmEmail2\" VARCHAR(40), \n\t\"AdmFName3\" VARCHAR(8), \n\t\"AdmLName3\" VARCHAR(15), \n\t\"AdmEmail3\" VARCHAR(39), \n\t\"LastUpdate\" DATE NOT NULL, \n\tCHECK (\"Charter\" IN (0, 1)), \n\tCHECK (\"Magnet\" IN (0, 1))\n)", "col_names": [ "CDSCode", "NCESDist", "NCESSchool", "StatusType", "County", "District", "School", "Street", "StreetAbr", "City", "Zip", "State", "MailStreet", "MailStrAbr", "MailCity", "MailZip", "MailState", "Phone", "Ext", "Website", "OpenDate", "ClosedDate", "Charter", "CharterNum", "FundingType", "DOC", "DOCType", "SOC", "SOCType", "EdOpsCode", "EdOpsName", "EILCode", "EILName", "GSoffered", "GSserved", "Virtual", "Magnet", "Latitude", "Longitude", "AdmFName1", "AdmLName1", "AdmEmail1", "AdmFName2", "AdmLName2", "AdmEmail2", "AdmFName3", "AdmLName3", "AdmEmail3", "LastUpdate" ], "questions": [ "1. What is the trend in the number of CDSCode in cdeschools.schools over time?", "2. How many NCESDist are available in cdeschools.schools?", "3. What is the most used StatusType in cdeschools.schools?", "4. Which County has the highest number of Districts in cdeschools.schools? ", "5. What is the average number of Schools per District in cdeschools.schools?", "6. What is the most common City mentioned in cdeschools.schools?", "7. How often is the MailState different from the State in cdeschools.schools?", "8. What is the average Phone number length in cdeschools.schools?", "9. Are there any Schools that do not have a Website in cdeschools.schools?", "10. How many Virtual Schools are listed in cdeschools.schools?", "11. How many Magnet Schools are offered in cdeschools.schools?", "12. What is the correlation between Latitude and Longitude in cdeschools.schools?", "13. How many Administrators are listed in cdeschools.schools?", "14. How many schools have an EdOpsName associated with them in cdeschools.schools?", "15. Are there any ClosedDate entered for Schools in cdeschools.schools?", "16. Has the FundingType for Schools changed over the years in cdeschools.schools?", "17. How many unique EILName are used in cdeschools.schools?", "18. What is the average GSserved value in cdeschools.schools?", "19. How often do the DOC, DOCType, SOC, and SOCType values match in cdeschools.schools?", "20. How often are the LastUpdate values updated in cdeschools.schools?" ] }, { "database": "cdeschools", "table": "frpm", "sql": "CREATE TABLE frpm (\n\t\"Academic Year\" VARCHAR(9), \n\t\"County Code\" VARCHAR(4), \n\t\"District Code\" INT(11), \n\t\"School Code\" VARCHAR(7), \n\t\"County Name\" VARCHAR(15), \n\t\"District Name\" VARCHAR(75), \n\t\"School Name\" VARCHAR(85), \n\t\"District Type\" VARCHAR(32), \n\t\"School Type\" VARCHAR(41), \n\t\"Educational Option Type\" VARCHAR(43), \n\t\"NSLP Provision Status\" VARCHAR(24), \n\t\"Charter School (Y/N)\" BOOLEAN, \n\t\"Charter School Number\" VARCHAR(4), \n\t\"Charter Funding Type\" VARCHAR(23), \n\t\"IRC\" BOOLEAN, \n\t\"Low Grade\" VARCHAR(5), \n\t\"High Grade\" VARCHAR(14), \n\t\"Enrollment (K-12)\" FLOAT, \n\t\"Free Meal Count (K-12)\" FLOAT, \n\t\"Percent (%) Eligible Free (K-12)\" FLOAT, \n\t\"FRPM Count (K-12)\" FLOAT, \n\t\"Percent (%) Eligible FRPM (K-12)\" FLOAT, \n\t\"Enrollment (Ages 5-17)\" FLOAT, \n\t\"Free Meal Count (Ages 5-17)\" FLOAT, \n\t\"Percent (%) Eligible Free (Ages 5-17)\" FLOAT, \n\t\"FRPM Count (Ages 5-17)\" FLOAT, \n\t\"Percent (%) Eligible FRPM (Ages 5-17)\" FLOAT, \n\t\"2013-14 CALPADS Fall 1 Certification Status\" BOOLEAN, \n\tCHECK (\"Charter School (Y/N)\" IN (0, 1)), \n\tCHECK (\"IRC\" IN (0, 1)), \n\tCHECK (\"2013-14 CALPADS Fall 1 Certification Status\" IN (0, 1))\n)", "col_names": [ "Academic Year", "County Code", "District Code", "School Code", "County Name", "District Name", "School Name", "District Type", "School Type", "Educational Option Type", "NSLP Provision Status", "Charter School (Y/N)", "Charter School Number", "Charter Funding Type", "IRC", "Low Grade", "High Grade", "Enrollment (K-12)", "Free Meal Count (K-12)", "Percent (%) Eligible Free (K-12)", "FRPM Count (K-12)", "Percent (%) Eligible FRPM (K-12)", "Enrollment (Ages 5-17)", "Free Meal Count (Ages 5-17)", "Percent (%) Eligible Free (Ages 5-17)", "FRPM Count (Ages 5-17)", "Percent (%) Eligible FRPM (Ages 5-17)", "2013-14 CALPADS Fall 1 Certification Status" ], "questions": [ "1. What is the average percentage of students eligible for FRPM in each district?", "2. How does the school type vary for each district type?", "3. What is the relation between the IRC and the FRPM count of students?", "4. What possible correlations exist between the low grade and high grade of a school and FRPM count?", "5. What educational options are offered in each school district?", "6. How has the change in the free meal count among students aged 5-17 in each school compared to other schools in the same district? ", "7. For which counties have the FRPM counts changed the most over the past 3-4 years?", "8. In 2013-14, what was the distribution of FRPM Eligible Free students across all districts?", "9. What are the differences between County Code and District Code in terms of FRPM eligibility? ", "10. For each district type, is there a relation between school enrolment and free meal count?", "11. Has the NSLP Provision Status affected the percentage of students eligible for FRPM over the years?", "12. What is the correlation between Charter School Number and Charter Funding Type for each school district?", "13. How has High Grade changed in relation to FRPM Count among students aged 5-17?", "14. What is the average change in Enrollment (Ages 5-17) from 2013-2014 across all counties?", "15. What is the average percentage of Free Meal Count (K-12) for each District Type?", "16. What is the relation between the district type and the education option type?", "17. How does the relation between County Name and District Name impact FRPM eligibility?", "18. How does the Charter School Number affect the Charter Funding Type?", "19. Does Free Meal Count (Ages 5-17) correspond with CALPADS Fall 1 Certification Status?", "20. What patterns exist in relation to Low Grade and FRPM Count (K-12)?" ] }, { "database": "cdeschools", "table": "satscores", "sql": "CREATE TABLE satscores (\n\tcds VARCHAR(14) NOT NULL, \n\trtype VARCHAR(1) NOT NULL, \n\tsname VARCHAR(50), \n\tdname VARCHAR(50), \n\tcname VARCHAR(15), \n\tenroll12 INT(11) NOT NULL, \n\t\"NumTstTakr\" INT(11) NOT NULL, \n\t\"AvgScrRead\" INT(11), \n\t\"AvgScrMath\" INT(11), \n\t\"AvgScrWrite\" INT(11), \n\t\"NumGE1500\" INT(11), \n\t\"PctGE1500\" FLOAT\n)", "col_names": [ "cds", "rtype", "sname", "dname", "cname", "enroll12", "NumTstTakr", "AvgScrRead", "AvgScrMath", "AvgScrWrite", "NumGE1500", "PctGE1500" ], "questions": [ "1. What is the average reading, math, and writing scores for all schools in the cdeschools.satscores table?", "2. What are the top 5 schools with the highest average reading scores?", "3. What is the average NumTstTakr for all schools in the cdeschools.satscores table?", "4. Which district has the greatest number of schools with Total NumGE1500 scores above the 75th percentile?", "5. How many schools have an average reading score higher than 700?", "6. Which district had the highest average combined math, reading, and writing scores?", "7. What is the average Total NumGE1500 scores across all districts?", "8. What is the difference in Average ScrRead scores between the 5th and 95th percentile?", "9. What is the total enroll12 across all schools?", "10. What is the average AvgScrWrite by cname?", "11. How do the AvgScrRead and AvgScrMath scores compare between urban, suburban, and rural schools?", "12. How many schools have an AvgScrWrite score of 1000 or higher?", "13. What is the average AvgScrMath by rtype?", "14. How many schools in each district have enroll12s lower than 500?", "15. What is the total NumGE1500 across all schools?", "16. What is the average AvgScrRead for schools with enroll12s above the 90th percentile?", "17. What is the range of AvgScrMath scores across all schools?", "18. Which district has the highest Total NumGE1500?", "19. How does the Average ScrRead differ between large schools (enroll12s above 500) and small schools (enroll12s below 500)?", "20. What is the PctGE1500 distribution across all schools?" ] }, { "database": "census2000names", "table": "surnames", "sql": "CREATE TABLE surnames (\n year INT(11) NOT NULL, \n name TEXT, \n rank INT(11) , \n count INT(11), \n prop100k FLOAT, \n cum_prop100k FLOAT, \n pctwhite FLOAT, \n pctblack FLOAT, \n pctapi FLOAT, \n pctaian FLOAT, \n pct2prace FLOAT, \n pcthispanic FLOAT\n)", "col_names": [ "year", "name", "rank", "count", "prop100k", "cum_prop100k", "pctwhite", "pctblack", "pctapi", "pctaian", "pct2prace", "pcthispanic" ], "questions": [ "1. What is the most common surname in 2000?", "2. What is the average rank of surnames of 2000?", "3. What are the top 5 surnames in 2000 with the highest prop100k?", "4. What percentage of surnames in 2000 has a prop100k greater than 50?", "5. What percentage of the surnames in 2000 has the same cum_prop100k?", "6. What is the average percentage of white surnames in 2000?", "7. What is the average percentage of black surnames in 2000?", "8. What is the average percentage of API surnames in 2000?", "9. What is the average percentage of AIAN surnames in 2000?", "10. What is the average percentage of 2prace surnames in 2000?", "11. What is the average percentage of Hispanic surnames in 2000?", "12. What proportion of the total surnames of 2000 are within the top 100 ranks?", "13. What is the ratio of prop100k between the first and the last surname in 2000?", "14. What is the largest leap in cumulative prop100k for any name in 2000?", "15. What is the average count for Hispanic surnames in 2000?", "16. What proportion of the surnames in 2000 have a prop100k above 0.5?", "17. What proportion of the names in 2000 have a rank of 10 or lower?", "18. What is the distribution of surname population by the different racial categories in 2000?", "19. What proportion of the surnames in 2000 has a count value above 500?", "20. What is the median compounded growth rate of all surnames in 2000?" ] }, { "database": "dallas_ois", "table": "incidents", "sql": "CREATE TABLE incidents (\n case_number TEXT , \n date DATE , \n location TEXT , \n subject_statuses TEXT , \n subject_weapon TEXT , \n subjects TEXT , \n subject_count INT(11) , \n officers TEXT , \n officer_count INT(11) , \n grand_jury_disposition TEXT, \n attorney_general_forms_url TEXT, \n summary_url TEXT, \n summary_text TEXT, \n latitude FLOAT, \n longitude FLOAT\n)", "col_names": [ "case_number", "date", "location", "subject_statuses", "subject_weapon", "subjects", "subject_count", "officers", "officer_count", "grand_jury_disposition", "attorney_general_forms_url", "summary_url", "summary_text", "latitude", "longitude" ], "questions": [ "1. What is the average number of subjects in Dallas OIS incidents? ", "2. How many OIS incidents have occurred in Dallas each year?", "3. What is the most common subject status in OIS incidents in Dallas?", "4. What is the average longitude and latitude of OIS incidents in Dallas?", "5. How many OIS incidents in Dallas had multiple subjects?", "6. How has the number of Dallas OIS incidents with weapons changed over time? ", "7. What is the most common weapon used in Dallas OIS incidents?", "8. Which Dallas locations have the highest number of OIS incidents?", "9. How often are Dallas OIS incidents presented for grand jury disposition? ", "10. How often are attorney general forms provided for Dallas OIS incidents?", "11. How often does the summary text for Dallas OIS incidents match what is provided on the summary URL? ", "12. What is the distribution of OIS incidents per officer in Dallas? ", "13. Are there any particular days on which Dallas OIS incidents are more common than others?", "14. Is there any difference in reported officer genders in Dallas OIS incidents?", "15. How often do Dallas OIS incidents involve the use of drugs or alcohol?", "16. How many Dallas OIS incidents are recorded without a summary URL or summary text?", "17. How do Dallas OIS incident latitudes and longitudes compare to the locations they are recorded in?", "18. What is the most common outcome of an officer-involved shooting in Dallas? ", "19. How often do subjects in Dallas OIS incidents have prior criminal history? ", "20. How many Dallas OIS incidents occur with subject counts of more than three people?" ] }, { "database": "dallas_ois", "table": "officers", "sql": "CREATE TABLE officers (\n case_number TEXT , \n race TEXT, \n gender TEXT , \n last_name TEXT , \n first_name TEXT, \n full_name TEXT \n)", "col_names": [ "case_number", "race", "gender", "last_name", "first_name", "full_name" ], "questions": [ "1. What is the total number of Dallas OIS officers registered in this database?", "2. What is the breakdown of race and gender of Dallas OIS officers?", "3. Are there any officers in this database with the same last name and first name?", "4. What is the distribution of full names among Dallas OIS officers?", "5. Does the database contain any officers with a first or last name that is shared by more than one officer?", "6. Are Dallas OIS officers registered by case number or by full name?", "7. How many officers have the same first and last name in this database?", "8. Over the years, has there been any change in the ethnic composition of Dallas OIS officers?", "9. What is the distribution of genders among the different racial groups in Dallas OIS officers?", "10. How often do officers with the same last name share a first name in this database?", "11. What is the most common first name among Dallas OIS officers?", "12. Is there any correlation between the full name of an officer and their race or gender?", "13. Is there any narrowing of the gap between the number of male and female officers across different ethnic backgrounds?", "14. Are there any discernible patterns among Dallas OIS officers in terms of their last name, first name, and full name?", "15. What is the longest full name registered for a Dallas OIS officer?", "16. Are there any officers with a long and complicated first name in this database?", "17. How has the frequency of Dallas OIS officers with a particular last name changed over time?", "18. Does the database contain any officers with strikingly similar first, last, or full names?", "19. Are there any racial or gender imbalances in the distribution of case numbers in Dallas OIS officers?", "20. How many times is the most commonly used full name repeated amongst Dallas OIS officers?" ] }, { "database": "dallas_ois", "table": "subjects", "sql": "CREATE TABLE subjects (\n case_number TEXT , \n race TEXT, \n gender TEXT ,\n last_name TEXT , \n first_name TEXT, \n full_name TEXT \n)", "col_names": [ "case_number", "race", "gender", "last_name", "first_name", "full_name" ], "questions": [ "1. What is the proportion of men to women involved in the Dallas OIS subjects?", "2. Is there any correlation between race and gender with the Dallas OIS subjects?", "3. Are there any statistical trends in the Dallas OIS subjects’ last names?", "4. Are there any patterns in the case numbers associated with each Dallas OIS subjects?", "5. How has the number of Dallas OIS subjects changed over time?", "6. What is the most common race of the Dallas OIS subjects?", "7. Do first names of Dallas OIS subjects vary according to race?", "8. Are there any correlation between first names and case numbers of the Dallas OIS subjects?", "9. Are there any differences in gender between different races of the Dallas OIS subjects?", "10. Does the frequency of last name occurances amongst Dallas OIS subjects differ by gender?", "11. Is there any relationship between race and case numbers of the Dallas OIS subjects?", "12. Are the full names of Dallas OIS subjects repeated for different cases?", "13. What is the most common gender among the Dallas OIS subjects?", "14. Is there any pattern in the first names of the Dallas OIS subjects in terms of their race?", "15. Are the last names of Dallas OIS subjects associated with certain races?", "16. Are there any correlations between full names and case numbers of the Dallas OIS subjects?", "17. What is the distribution of the Dallas OIS subjects' race by gender?", "18. Has the gender of Dallas OIS subjects shifted over time?", "19. Has there been a noticeable change in the proportion of Dallas OIS subjects' full names over time?", "20. Are there any relationships between first names and last names of the Dallas OIS subjects?" ] }, { "database": "acs_1_year_2015", "table": "states", "sql": "CREATE TABLE states (\n year INT(11) , \n name TEXT , \n geo_id TEXT , \n total_population INT(11) , \n white INT(11) , \n black INT(11) , \n hispanic INT(11) , \n asian INT(11) , \n american_indian INT(11) , \n pacific_islander INT(11) , \n other_race INT(11) , \n median_age FLOAT , \n total_households INT(11) , \n owner_occupied_homes_median_value INT(11) , \n per_capita_income INT(11) , \n median_household_income INT(11) , \n below_poverty_line INT(11), \n foreign_born_population INT(11), \n state TEXT \n)", "col_names": [ "year", "name", "geo_id", "total_population", "white", "black", "hispanic", "asian", "american_indian", "pacific_islander", "other_race", "median_age", "total_households", "owner_occupied_homes_median_value", "per_capita_income", "median_household_income", "below_poverty_line", "foreign_born_population", "state" ], "questions": [ "1. What is the total population and median age for each state?", "2. What is the racial breakdown of each state in terms of white, black, Hispanic, Asian, American Indian and Pacific Islander?", "3. What is the median value of owner-occupied homes in each state?", "4. How does per capita income vary between states?", "5. Which states have the highest and lowest median household incomes?", "6. How does the prevalence of population living under the poverty line vary between states?", "7. How does the foreign-born population vary between states?", "8. How does the total households compares between states?", "9. What is the racial breakdown in terms of total population size in each state?", "10. What is the median income of owner-occupied households in each state?", "11. What is the median age distribution of the population in each state?", "12. How does the ratio of owner-occupied homes to total households vary between states?", "13. What is the magnitude of proportion of the each race to total population in each state?", "14. How does per capita income vary between states within a given geography (e.g. east coast, middle america, etc)?", "15. How does the rate of poverty vary between states within a given region (e.g. rural, suburban, etc)?", "16. How does the racial composition of owner-occupied households vary between states in America?", "17. What are the foreign-born population percentages for each state?", "18. Are there any common economic or demographic features that are shared among specific states?", "19. How do states compare in terms of total population, total households and median household income combined?", "20. What are the average populations per state in terms of total population and each individual races?" ] }, { "database": "acs_1_year_2015", "table": "congressional_districts", "sql": "CREATE TABLE congressional_districts (\n year INT(11) , \n name TEXT , \n geo_id TEXT , \n total_population INT(11) , \n white INT(11) , \n black INT(11) , \n hispanic INT(11) , \n asian INT(11) , \n american_indian INT(11) , \n pacific_islander INT(11) , \n other_race INT(11) , \n median_age FLOAT , \n total_households INT(11) , \n owner_occupied_homes_median_value INT(11) , \n per_capita_income INT(11) , \n median_household_income INT(11) , \n below_poverty_line INT(11), \n foreign_born_population INT(11), \n state TEXT,\n congressional_district TEXT\n)", "col_names": [ "year", "name", "geo_id", "total_population", "white", "black", "hispanic", "asian", "american_indian", "pacific_islander", "other_race", "median_age", "total_households", "owner_occupied_homes_median_value", "per_capita_income", "median_household_income", "below_poverty_line", "foreign_born_population", "state", "congressional_district" ], "questions": [ "1. How much was the total population in Congressional Districts in 2015? ", "2. What is the median age of Congressional Districts in 2015? ", "3. What is the total number of households in Congressional Districts in 2015? ", "4. What is the median value of owner-occupied homes in Congressional Districts in 2015? ", "5. What is the median household income across Congressional Districts in 2015? ", "6. What percentage of the population in Congressional Districts was below the poverty line in 2015? ", "7. How many people in Congressional Districts were foreign-born in 2015? ", "8. What is the racial breakdown of people in Congressional Districts in 2015? ", "9. What is the per capita income in Congressional Districts in 2015? ", "10. What is the median age of White people in Congressional Districts in 2015? ", "11. What is the median age of Black people in Congressional Districts in 2015? ", "12. What is the median age of Hispanic people in Congressional Districts in 2015? ", "13. What is the median age of Asian people in Congressional Districts in 2015? ", "14. What is the median age of American Indian people in Congressional Districts in 2015? ", "15. What is the median age of Pacific Islander people in Congressional Districts in 2015? ", "16. What is the median household income of White people in Congressional Districts in 2015? ", "17. What is the median household income of Black people in Congressional Districts in 2015? ", "18. What is the median household income of Hispanic people in Congressional Districts in 2015? ", "19. What percentage of the population in Congressional Districts was foreign-born in 2015? ", "20. What is the owner-occupied homes median value for the states comprising Congressional Districts in 2015?" ] }, { "database": "acs_1_year_2015", "table": "places", "sql": "CREATE TABLE places (\n year INT(11) , \n name TEXT , \n geo_id TEXT , \n total_population INT(11) , \n white INT(11) , \n black INT(11) , \n hispanic INT(11) , \n asian INT(11) , \n american_indian INT(11) , \n pacific_islander INT(11) , \n other_race INT(11) , \n median_age FLOAT , \n total_households INT(11) , \n owner_occupied_homes_median_value INT(11) , \n per_capita_income INT(11) , \n median_household_income INT(11) , \n below_poverty_line INT(11), \n foreign_born_population INT(11), \n state TEXT,\n place TEXT\n)", "col_names": [ "year", "name", "geo_id", "total_population", "white", "black", "hispanic", "asian", "american_indian", "pacific_islander", "other_race", "median_age", "total_households", "owner_occupied_homes_median_value", "per_capita_income", "median_household_income", "below_poverty_line", "foreign_born_population", "state", "place" ], "questions": [ "1. What is the racial composition of places in the US in 2015?", "2. What is the median age of places in the US in 2015? ", "3. How much higher is the median owner-occupied homes median value compared to the median household income?", "4. What is the total population of each place in the US in 2015? ", "5. What is the median household income of each place in the US in 2015? ", "6. What was the foreign born population in the US in 2015? ", "7. What percentage of population in each place in the US in 2015 is below the poverty line?", "8. What are the differences in median household income between each state? ", "9. Which states have the highest and lowest owner-occupied homes median value in 2015?", "10. Which states have the most and least white population in 2015?", "11. What places have the most and least asian population in 2015?", "12. Which states have the highest and lowest total population in 2015? ", "13. What are the differences in median age between each state?", "14. What places have the highest and lowest median household incomes in 2015? ", "15. What places have the largest and smallest populations of American Indians in 2015?", "16. How is the per capita income in each state distributed?", "17. What places have the most and least black population in 2015?", "18. What places have the highest and lowest median owner-occupied homes median value in 2015?", "19. What are the distribution of foreign born population in each place in the US in 2015?", "20. What places have the highest percentage of people below the poverty line in 2015?" ] } ]