In paul4forest/tradeflows: Process forest products trade flow data from COMTRADE and COMEXT

library(knitr)
opts_knit$set(root.dir="../../..") # file paths are relative to the root of the project directory
opts_chunk$set(echo=TRUE, warning=FALSE)
library(tradeflows)
library(dplyr)
library(ggplot2)
library(reshape2)

Simo's message from August 10

Simo:

the first validation did not produce same number of rows:

37415 rows in the raw table became 33280 rows in the validated table.

The attachment is that raw table.

Investigating fuel wood data

I renamed "raw_flow_yearly" to "raw_flow_fuelwood" and Loaded the raw table into Mysql with the command:

cat raw_flow_fuelwood.sql | mysql -u paul -p tradeflows

fw <- readdbtbl("raw_flow_fuelwood")
fwprod <- fw %>% group_by(productcode) %>%
    summarise(nrow = n()) %>% 
    arrange(desc(nrow)) %>% data.frame()
fwprod %>% kable
# Are there duplicates?
fwdall <- fw %>% collect()
findduplicatedflows(fwdall)

Cleaning fuel wood data

# Add column to the column definitions to avoid complains
column_names$raw_flow_fuelwood <- column_names$raw_flow_yearly
# Clean one of the product in this table
cleandbproduct(440130, tableread =  "raw_flow_fuelwood", tablewrite = "validated_flow_yearly")
cleandbproduct(440110, tableread =  "raw_flow_fuelwood", tablewrite = "validated_flow_yearly")
cleandbproduct(440122, tableread =  "raw_flow_fuelwood", tablewrite = "validated_flow_yearly")
cleandbproduct( 440121, tableread =  "raw_flow_fuelwood", tablewrite = "validated_flow_yearly")
cleandbproduct( 440320, tableread =  "raw_flow_fuelwood", tablewrite = "validated_flow_yearly")
cleandbproduct(440290, tableread =  "raw_flow_fuelwood", tablewrite = "validated_flow_yearly")
cleandbproduct(440200, tableread =  "raw_flow_fuelwood", tablewrite = "validated_flow_yearly")

Compare number of rows in the raw and validated datasets

fwraw <- readdbtbl("raw_flow_fuelwood") %>%
    group_by(productcode) %>%
    summarise(raw_lines = n()) %>% 
    arrange(desc(raw_lines)) %>% data.frame()

fwvalidated <- readdbtbl("validated_flow_yearly") %>%
    filter(productcode %in% fwraw$productcode) %>%
    group_by(productcode) %>%
    summarise(validated_lines = n()) %>% 
    arrange(desc(validated_lines)) %>% data.frame() %>%
    merge(fwraw)
fwvalidated %>% kable

| productcode| nrow| |-----------:|-----:| | 440130| 13763| | 440110| 7317| | 440122| 7232| | 440121| 4968| | 440320| 1507| | 440290| 1379| | 440200| 1249|

no reim port and re export

readdbtbl("raw_flow_fuelwood") %>%
    filter(flow %in% c("Import","Export")) %>%
    group_by(productcode) %>%
    summarise(raw_lines = n()) %>% 
    arrange(desc(raw_lines)) %>% data.frame()

paul4forest/tradeflows documentation built on Oct. 8, 2019, 10:35 a.m.