From cbc1c08350f3046971f26d68d67f4f18971d77b7 Mon Sep 17 00:00:00 2001
From: coolneng <akasroua@gmail.com>
Date: Mon, 6 Jan 2020 06:34:35 +0100
Subject: [PATCH] Add csv parser

---
 code/database/db_setup.py                 |  6 +++---
 code/database/{parse_csv.py => parser.py} | 19 +++++++++++++++----
 code/database/storage.py                  |  0
 docs/Project.org                          |  2 +-
 4 files changed, 19 insertions(+), 8 deletions(-)
 rename code/database/{parse_csv.py => parser.py} (59%)
 create mode 100644 code/database/storage.py

diff --git a/code/database/db_setup.py b/code/database/db_setup.py
index c50c8f6..6da3d48 100644
--- a/code/database/db_setup.py
+++ b/code/database/db_setup.py
@@ -30,8 +30,8 @@ db = create_connection()
 
 class Glacier(db.Model):
     uid = db.Column(db.Integer, primary_key=True)
-    country = db.Column(db.String(30))
-    name = db.Column(db.String(30))
+    country = db.Column(db.String(60))
+    name = db.Column(db.String(60))
 
     def __init__(self, uid, country, name):
         self.uid = uid
@@ -73,7 +73,7 @@ class Annual_Change(db.Model):
         self.year = year
 
 
-class Users(db.Model):
+class User(db.Model):
     uid = db.Column(db.Integer, primary_key=True)
     registration_date = db.Column(db.DateTime, nullable=False)
 
diff --git a/code/database/parse_csv.py b/code/database/parser.py
similarity index 59%
rename from code/database/parse_csv.py
rename to code/database/parser.py
index ecbb551..1b85a71 100644
--- a/code/database/parse_csv.py
+++ b/code/database/parser.py
@@ -1,5 +1,6 @@
-from pandas import read_csv, concat, DataFrame
 from iso3166 import countries as co
+from pandas import DataFrame, concat, read_csv
+from csv import QUOTE_NONNUMERIC
 
 
 def country_conversion(political_unit) -> str:
@@ -15,16 +16,26 @@ def select_columns() -> DataFrame:
         "YEAR",
         "AREA_SURVEY_YEAR",
         "AREA_CHANGE",
-        "THICKNESS CHANGE",
+        "THICKNESS_CHG",
         "VOLUME_CHANGE",
     ]
     iter_csv = read_csv(
-        "../../data/WGMS-FoG-2019-12-D-CHANGE.csv",
+        "../data/WGMS-FoG-2019-12-D-CHANGE.csv",
         skipinitialspace=True,
         usecols=fields,
         iterator=True,
         chunksize=100,
-        converters={"YEAR": country_conversion},
+        converters={"POLITICAL_UNIT": country_conversion},
     )
     data = concat([chunk[chunk["YEAR"] > min_year] for chunk in iter_csv])
     return data
+
+
+def main():
+    df = select_columns()
+    database = "../data/igdb.csv"
+    df.to_csv(database, index=False, quoting=QUOTE_NONNUMERIC)
+
+
+if __name__ == "__main__":
+    main()
diff --git a/code/database/storage.py b/code/database/storage.py
new file mode 100644
index 0000000..e69de29
diff --git a/docs/Project.org b/docs/Project.org
index 6fb7220..764ff73 100644
--- a/docs/Project.org
+++ b/docs/Project.org
@@ -18,7 +18,7 @@ datos relevantes para estudios acerca del cambio climático, y acotando éstos a
 *** Datos
 
 1. *RD1*: Datos del glaciar
-   - País - /Cadena de 30 caracteres máximo/
+   - País - /Cadena de 60 caracteres máximo/
    - Nombre del glaciar - /Cadena de 60 caracteres máximo/
    - ID del glaciar (Compatible con la WGMS) - /Entero de 5 dígitos/