kaggle比赛实践M5-baseline研读

# Correct data types for "calendar.csv"
calendarDTypes = {"event_name_1": "category", 
                  "event_name_2": "category", 
                  "event_type_1": "category", 
                  "event_type_2": "category", 
                  "weekday": "category", 
                  ‘wm_yr_wk‘: ‘int16‘, 
                  "wday": "int16",
                  "month": "int16", 
                  "year": "int16", 
                  "snap_CA": "float32", 
                  ‘snap_TX‘: ‘float32‘, 
                  ‘snap_WI‘: ‘float32‘ }

# Read csv file
calendar = pd.read_csv("./calendar.csv", 
                       dtype = calendarDTypes)
calendar["date"] = pd.to_datetime(calendar["date"])
calendar.head(10)

# Transform categorical features into integers
for col, colDType in calendarDTypes.items():
    if colDType == "category":
        calendar[col] = calendar[col].cat.codes.astype("int16")
        calendar[col] -= calendar[col].min()

calendar.head(10)

# Correct data types for "sell_prices.csv"
priceDTypes = {"store_id": "category", 
               "item_id": "category", 
               "wm_yr_wk": "int16",
               "sell_price":"float32"}

# Read csv file
prices = pd.read_csv("./sell_prices.csv", 
                     dtype = priceDTypes)

prices.head()

# Transform categorical features into integers
for col, colDType in priceDTypes.items():
    if colDType == "category":
        prices[col] = prices[col].cat.codes.astype("int16")
        prices[col] -= prices[col].min()
        
prices.head()

firstDay = 250
lastDay = 1913

# Use x sales days (columns) for training
numCols = [f"d_{day}" for day in range(firstDay, lastDay+1)]

# Define all categorical columns
catCols = [‘id‘, ‘item_id‘, ‘dept_id‘,‘store_id‘, ‘cat_id‘, ‘state_id‘]

# Define the correct data types for "sales_train_validation.csv"
dtype = {numCol: "float32" for numCol in numCols} 
dtype.update({catCol: "category" for catCol in catCols if catCol != "id"})

[(k,v)  for k,v in dtype.items()][:10]

# Read csv file
ds = pd.read_csv("./sales_train_validation.csv", 
                 usecols = catCols + numCols, dtype = dtype)

ds.head()

# Transform categorical features into integers
for col in catCols:
    if col != "id":
        ds[col] = ds[col].cat.codes.astype("int16")
        ds[col] -= ds[col].min()
        
ds = pd.melt(ds,
             id_vars = catCols,
             value_vars = [col for col in ds.columns if col.startswith("d_")],
             var_name = "d",
             value_name = "sales")

# Merge "ds" with "calendar" and "prices" dataframe
ds = ds.merge(calendar, on = "d", copy = False)
ds = ds.merge(prices, on = ["store_id", "item_id", "wm_yr_wk"], copy = False)

ds.head()