Merge pull request #659 from plotly/optimize-csv-files

Optimize csv files

Former-commit-id: 9a8f6b9

Author: Xing Han Lu

.gitignore

@@ -12,4 +12,5 @@ apps/*/.ipynb_checkpoints/*
 apps/*/__pycache__/*
 apps/dash-tsne/data
 apps/dash-tsne/demo_embeddings
+temp.py
 temp.sh

apps/dash-baseball-statistics/data.py

@@ -14,9 +14,9 @@
 # for easier display of historical team data
 teams = pd.read_csv("data/update_team.csv")
 # Import Players batting data
-batters = pd.read_csv("data/update_batting.csv")
+batters = pd.read_csv("data/update_batting.csv.gz")
 # Import custom Fielding data
-fielding = pd.read_csv("data/update_fielding.csv")
+fielding = pd.read_csv("data/update_fielding.csv.gz")
 # Import custom pitching data
 pitching = pd.read_csv("data/update_pitching.csv")
 # Import Player profile data

apps/dash-baseball-statistics/data/update_batting.csv.REMOVED.git-id

@@ -23,7 +23,7 @@
 DATA_PATH = BASE_PATH.joinpath("data").resolve()
 
 # Read data
-df = pd.read_csv(DATA_PATH.joinpath("clinical_analytics.csv"))
+df = pd.read_csv(DATA_PATH.joinpath("clinical_analytics.csv.gz"))
 
 clinic_list = df["Clinic Name"].unique()
 df["Admit Source"] = df["Admit Source"].fillna("Not Identified")

apps/dash-baseball-statistics/data/update_batting.csv.gz

@@ -15,7 +15,7 @@
 # Dataset Processing
 
 # importing data
-data = pd.read_csv("archive/players_21.csv")
+data = pd.read_csv("archive/players_21.csv.gz")
 
 # data cleaning
 nonusefulcolumns = ["sofifa_id", "player_url", "long_name", "league_rank"]