101 Python datatable Exercises (pydatatable)

import datatable as dt
dt.__version__

'0.8.0'

import pandas as pd
import numpy as np
import datatable as dt

# Inputs
my_list = list('abcedfghijklmnopqrstuvwxyz')
my_arr  = np.arange(26)
my_df   = pd.DataFrame(dict(col1=my_list, col2=my_arr))


# Solution
dt_df1  = dt.Frame(my_list)
dt_df2  = dt.Frame(my_arr)
dt_df3  = dt.Frame(my_df)
dt_df4  = dt.Frame(A=my_arr, B= my_list)

# Solution
import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/BostonHousing.csv')
df.head(5)

# Solution
import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/BostonHousing.csv', max_nrows= 5)
df

# Input
import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/BostonHousing.csv', max_nrows= 5)

# Solution
df[:,"new_column"] = dt.Frame([1,2,3,4,5])
df

# Input
import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/BostonHousing.csv')

# Solution
df[:,"new_column"] = df[:, dt.f.age + dt.f.rad]

# Input
import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/BostonHousing.csv')

# Solution
df[:, "new_column"] = df[:, dt.int32(dt.f.dis)]
df.head(5)

import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/BostonHousing.csv')
df[:, "new_column"] = dt.Frame(np.where(df[:, dt.f.age > 60], 'Old', 'New'))
df.head(5)

import datatable as dt
df1 = dt.Frame(A=[1,2,3,4],B=["a", "b", "c", "d"])
df2 = dt.Frame(A=[1,2,3,4,5],C=["a2", "b2", "c2", "d2", "e2"])
df2.key = "A"
output = df1[:, :, dt.join(df2)]
output

import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/BostonHousing.csv')
df.names = {'zn': 'zn_new'}
df.head(5)

# Solution: Use csv reader. Unfortunately there isn't an option to do it directly using fread()
import datatable as dt
import csv          
with open('local/path/to/BostonHousing.csv', 'r') as f:
    reader = csv.reader(f)
    for i, row in enumerate(reader):
        row = [[x] for x in row]
        # 1st row
        if i == 0:  
            df = dt.Frame(row)
            header = [x[0] for x in df[0,:].to_list()]
            df.names =  header
            del df[0,:]  
        # Every 50th row
        elif i%50 ==0:
            df_temp = dt.Frame(row)
            df_temp.names = header
            df.rbind(df_temp)

df.head(5)

# Solution: Use csv reader
import datatable as dt
import csv          
with open('https://raw.githubusercontent.com/selva86/datasets/master/BostonHousing.csv', 'r') as f:
    reader = csv.reader(f)
    for i, row in enumerate(reader):
        row = [[x] for x in row]
        if i == 0:
            df = dt.Frame(row)
            header = [x[0] for x in df[0,:].to_list()]
            df.names =  header
            del df[0,:]  
        else:
            row[13] = ['High'] if float(row[13][0]) > 25 else ['Low']
            df_temp = dt.Frame(row)
            df_temp.names = header
            df.rbind(df_temp)

df.head(5)

# Solution: It follows row, column indexing. No need to use "loc", ".loc"
import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/BostonHousing.csv')
df[2,1] = 5
df.head(5)

# Solution: It follows row,colume indexing. No need to use "loc", ".loc"
import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/BostonHousing.csv')

# Delete the cell at position `2,1`.
del df[2,1]

# Delete the `3rd` row.
del df[3,:]

# Delete the `chas` column.
del df[:,"chas"]

# Delete rows where column `zn` is having 0 value.
del df[dt.f.zn == 0,:]

df.head(5)

# Solution
import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/BostonHousing.csv')

# to pandas df
pd_df = df.to_pandas()

# to numpy arrays
np_arrays = df.to_numpy()

# to dictionary
dic = df.to_dict()

# to list
list_ = df[:,"indus"].to_list()

# to tuple
tuples_ = df[:,"indus"].to_tuples()

# to csv 
df.to_csv("BostonHousing.csv")

# Solution
import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/BostonHousing.csv')
for i in range(len(df.names)):
    print(df.names[i], ":", df.stypes[i])

crim : stype.float64
zn : stype.float64
indus : stype.float64
chas : stype.bool8
nox : stype.float64
rm : stype.float64
age : stype.float64
dis : stype.float64
rad : stype.int32
tax : stype.int32
ptratio : stype.float64
b : stype.float64
lstat : stype.float64
medv : stype.float64

# Solution
import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/BostonHousing.csv')
df.sum()
df.max()
df.min()
df.mean()
df.sd()
df.mode()
df.nmodal()
df.nunique()

# Input
import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/BostonHousing.csv')
df[:,dt.max(dt.f.zn)]

# Solution
import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/Cars93_miss.csv')
df[:, dt.mean(dt.f.Price), dt.by("Manufacturer")].head(5)

import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/Cars93_miss.csv')

# Solution1
df.sort("Price")

# Solution2
df[:,:, dt.sort(dt.f.Price)].head(5)

import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/Cars93_miss.csv')

# Solution
df[::-1,:, dt.sort(dt.f.Price)].head()

# Input
import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/Cars93_miss.csv')

# Solution
dt.repeat(df, 5)

# Input
import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/Cars93_miss.csv')

# Solution
df.replace("Audi", "My Dream Car")
df.head(5)

# Input
import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/Cars93_miss.csv')

# Solution

# Get the highest price
print("Highest Price : ", df[:,dt.f.Price].max()[0,0])

# Get Manufacturer with highest price
df[dt.f.Price ==  df[:,dt.f.Price].max()[0,0], ['Manufacturer', 'Model', 'Type']]

Highest Price :  61.9

# Input
import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/Cars93_miss.csv')

# Solution
old_col_name = "Model"
new_col_name = "Car Model"
df.names = [new_col_name if x == old_col_name else x for x in df.names]
df.head(5)

# Input
import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/Cars93_miss.csv')

# Solution
df.countna()

# Input
import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/Cars93_miss.csv')

# Solution
df[:,"Model"].head(5)

# Input
import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/Cars93_miss.csv')

# Solution 1
df.head()
df[:,::-1].head(5)

# Solution
import datatable as dt
df = dt.Frame(random=np.random.random(4)**10)
df[:,"random2"] = dt.Frame(['%.6f' % x for x in df[:,"random"].to_list()[0]])
df

# Input
import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/Cars93_miss.csv')

# Solution
df[::20, ['Manufacturer', 'Model', 'Type']]

# Input
import datatable as dt
df = dt.fread('https://raw.githubusercontent.com/selva86/datasets/master/Cars93_miss.csv')

# Solution
df[::-1,:]

# Input
import datatable as dt
df = dt.fread("https://raw.githubusercontent.com/selva86/datasets/master/BostonHousing.csv")

# Solution
for i in range(len(df.names)):
    if df.sum()[0:1,:].to_list()[i] == max(df.sum()[0:1,:].to_list()):
        print(df.names[i])

tax

# Input
import datatable as dt
df = dt.fread("BostonHousing.csv")

# Solution
for i in df.names:
    df[:,i] = df[:,(dt.f[i] - df[:,dt.min(dt.f[i])][0,0])/(df[:,dt.max(dt.f[i])][0,0] - df[:,dt.min(dt.f[i])][0,0])]
df.head(5)

# Input
import datatable as dt
df = dt.Frame(fruit = ['apple', 'banana', 'orange'] * 3,
             rating =  np.random.rand(9),
             price  =  np.random.randint(0, 15, 9))
df[:, dt.mean(dt.f.price), dt.by("fruit")]

# Input
import datatable as dt
df1 = dt.Frame(A=[1, 2, 3, 4], B=["a", "b", "c", "d"], D=[1, 2, 3, 4])
df2 = dt.Frame(A=[1, 2, 4, 5], B=["a", "b", "d", "e"], C=["a2", "b2", "d2", "e2"])

# Solution
df2.key = ["A","B"]
output = df1[:, :, dt.join(df2)]
output

# Input
import datatable as dt
df = dt.Frame(A=[1,2,3,4],B=["a", "b", "c", "d"],d=[1,2,3,4])

# Solution
dt.cbind(df1,df[1:,"A"],force= True)

import datatable as dt
from datatable.models import Ftrl

# Import data
train_df = dt.fread('pima_indian_diabetes_training_data.csv')
test_df = dt.fread('pima_indian_diabetes_testing_data.csv')

# Create Ftrl model
ftrl_model = Ftrl()

#  add parameter values while creating model
ftrl_model = Ftrl(alpha = 0.1, lambda1 = 0.5, lambda2 = 0.6)

# change paramter of existing model
ftrl_model.alpha = 0.1
ftrl_model.lambda1 = 0.5
ftrl_model.lambda2 = 0.6

# Prepare training and test dataset
train_df[:,"diabetes"] = dt.Frame(np.where(train_df[:, dt.f["diabetes"] == "pos"], 1,0))
test_df[:,"diabetes"] = dt.Frame(np.where(test_df[:, dt.f["diabetes"] == "pos"], 1,0))

x_train = train_df[:, ["pregnant", "glucose", "pressure", "mass", "pedigree", "age"]]
y_train = train_df[:, ["diabetes"]]

x_test = test_df[:, ["pregnant", "glucose", "pressure", "mass", "pedigree", "age"]]
y_test = test_df[:, ["diabetes"]]

# training the model
ftrl_model.fit(x_train,y_train)

# predictions of the model
targets = ftrl_model.predict(x_test)
print(targets.head(5))

# feature importance
fi = ftrl_model.feature_importances
fi