Add farm size.

cid-harvard · Jul 21, 2017 · 2be9c25 · 2be9c25
1 parent 5b47292
commit 2be9c25
Show file tree

Hide file tree

Showing 8 changed files with 56 additions and 2 deletions.
diff --git a/product/Datlas/Rural/Tupfile b/product/Datlas/Rural/Tupfile
@@ -5,10 +5,12 @@ AGPRODUCTS = in/AgProducts_Hierarchy.tsv in/AgProducts_Names.tsv
 AGPRODUCTS_CENSUS = in/AgProducts_Census_Hierarchy.tsv in/AgProducts_Census_Names.tsv
 FARMTYPE = in/FarmType_Hierarchy.tsv in/FarmType_Names.tsv
 LANDUSE = in/LandUse_Hierarchy.tsv in/LandUse_Names.tsv
+FARMSIZE = in/FarmSize_Hierarchy.tsv in/FarmSize_Names.tsv
 
-: |> $(PYTHON_PREFIX) download_sheets.py |> $(LIVESTOCK) $(AGPRODUCTS) $(AGPRODUCTS_CENSUS) $(FARMTYPE) $(LANDUSE)
+: |> $(PYTHON_PREFIX) download_sheets.py |> $(LIVESTOCK) $(AGPRODUCTS) $(AGPRODUCTS_CENSUS) $(FARMTYPE) $(LANDUSE) $(FARMSIZE)
 : $(LIVESTOCK) |> $(PYTHON_PREFIX) clean_livestock.py |> out/livestock.csv out/livestock.dta
 : $(AGPRODUCTS_CENSUS) |> $(PYTHON_PREFIX) clean_agproducts_census.py |> out/agricultural_products_census.csv out/agricultural_products_census.dta
 : $(AGPRODUCTS) |> $(PYTHON_PREFIX) clean_agproducts.py |> out/agricultural_products.csv out/agricultural_products.dta
 : $(FARMTYPE) |> $(PYTHON_PREFIX) clean_farmtype.py |> out/farm_type.csv out/farm_type.dta
 : $(LANDUSE) |> $(PYTHON_PREFIX) clean_landuse.py |> out/land_use.csv
+: $(FARMSIZE) |> $(PYTHON_PREFIX) clean_farmsizetype.py |> out/farm_size.csv out/farm_size.dta
diff --git a/product/Datlas/Rural/clean_farmsizetype.py b/product/Datlas/Rural/clean_farmsizetype.py
@@ -0,0 +1,35 @@
+import pandas as pd
+
+from classification import (Hierarchy, repeated_table_to_parent_id_table,
+                            parent_code_table_to_parent_id_table,
+                            Classification)
+
+if __name__ == "__main__":
+    names = pd.read_table("./in/FarmSize_Names.tsv", encoding="utf-8",
+                          dtype={"code": str})
+
+    hierarchy = pd.read_table("./in/FarmSize_Hierarchy.tsv", encoding="utf-8")
+    hierarchy.columns = ["level1_code", "level0_code"]
+
+    fields = {
+        "level0": [],
+        "level1": [],
+    }
+
+    h = Hierarchy(["level0", "level1"])
+    parent_code_table = repeated_table_to_parent_id_table(hierarchy, h, fields)
+    parent_code_table.code = parent_code_table.code.astype(str)
+
+    parent_code_table = parent_code_table.merge(names, on=["code", "level"])
+
+    parent_id_table = parent_code_table_to_parent_id_table(parent_code_table, h)
+    parent_id_table["name"] = parent_id_table.name_en
+
+    parent_id_table = parent_id_table[["code", "name", "level", "name_en",
+                                       "name_es", "name_short_en",
+                                       "name_short_es", "parent_id"]]
+
+    c = Classification(parent_id_table, h)
+
+    c.to_csv("out/farm_size.csv")
+    c.to_stata("out/farm_size.dta")
diff --git a/product/Datlas/Rural/download_sheets.py b/product/Datlas/Rural/download_sheets.py
@@ -25,3 +25,8 @@
 hierarchy, names = get_classification_from_gdrive("https://docs.google.com/spreadsheets/d/17EoKvwQKujYRCKzh2odu--bpR0d2grigrWDn4CjRaeg/edit#gid=1207195644")
 hierarchy.to_csv("./in/LandUse_Hierarchy.tsv", sep="\t", index=False, encoding="utf-8")
 names.to_csv("./in/LandUse_Names.tsv", sep="\t", index=False, encoding="utf-8")
+
+# Farmsize Type
+hierarchy, names = get_classification_from_gdrive("https://docs.google.com/spreadsheets/d/1ORWQDmc0wDPiOW4nBgi40JsKjL7tLm-YzaGBO6TP0Jk/edit#gid=1207195644")
+hierarchy.to_csv("./in/FarmSize_Hierarchy.tsv", sep="\t", index=False, encoding="utf-8")
+names.to_csv("./in/FarmSize_Names.tsv", sep="\t", index=False, encoding="utf-8")
diff --git a/product/Datlas/Rural/in/FarmSize_Hierarchy.tsv b/product/Datlas/Rural/in/FarmSize_Hierarchy.tsv
@@ -0,0 +1,3 @@
+level1	level0
+Agropecuario	Agropecuario o no agropecuario
+No agropecuario	Agropecuario o no agropecuario
diff --git a/product/Datlas/Rural/in/FarmSize_Names.tsv b/product/Datlas/Rural/in/FarmSize_Names.tsv
@@ -0,0 +1,4 @@
+code	level	name_en	name_short_en	name_es	name_short_es
+Agropecuario o no agropecuario	level0	Total	Total	Agropecuario o no agropecuario	Agropecuario o no agropecuario
+Agropecuario	level1	Agricultural	Agricultural	Agropecuario	Agropecuario
+No agropecuario	level1	Nonagricultural	Nonagricultural	No agropecuario	No agropecuario
diff --git a/product/Datlas/Rural/out/farm_size.csv b/product/Datlas/Rural/out/farm_size.csv
@@ -0,0 +1,4 @@
+"","code","name","level","name_en","name_es","name_short_en","name_short_es","parent_id"
+0,"Agropecuario o no agropecuario","Total","level0","Total","Agropecuario o no agropecuario","Total","Agropecuario o no agropecuario",""
+1,"Agropecuario","Agricultural","level1","Agricultural","Agropecuario","Agricultural","Agropecuario",0.0
+2,"No agropecuario","Nonagricultural","level1","Nonagricultural","No agropecuario","Nonagricultural","No agropecuario",0.0
diff --git a/product/Datlas/Rural/out/farm_size.dta b/product/Datlas/Rural/out/farm_size.dta
diff --git a/setup.py b/setup.py
@@ -2,7 +2,7 @@
 
 setup(
     name="linnaeus",
-    version="v0.0.78",
+    version="v0.0.79",
     author="Mali Akmanalp <Harvard CID>",
     description=("Harvard CID's classification tools."),
     url="http://github.com/cid-harvard/classifications/",
@@ -26,6 +26,7 @@
             'product/Datlas/Rural/out/agricultural_products.csv',
             'product/Datlas/Rural/out/agricultural_products_census.csv',
             'product/Datlas/Rural/out/farm_type.csv',
+            'product/Datlas/Rural/out/farm_size.csv',
             'product/HS/Atlas/out/hs92_atlas.csv',
             'product/HS/Mexico_Prospedia/out/products_mexico_prospedia.csv',
             'product/HS/Colombia_Prospedia/out/products_colombia_prospedia.csv',