Discussion on Predict the Missing Grade Challenge

Sort 23 Discussions, By:

3 years ago+ 1 comment

Parsing the .json file can be tricky, but json is available in Python for exactly this. This is one way that the module can be used:

import pandas as pd 
import json

num_lines = int(input())
inputs = [json.loads(input()) for _ in range(num_lines)]
test_df = pd.DataFrame(inputs).fillna(0)
with open('training.json') as f:
    data = [json.loads(line) for line in f]
    data.remove(data[0])
    train_df = pd.DataFrame(data).fillna(0)

Other minor points to note when submitting:

test and train may not have identical columns, and therefore need to be aligned
the marker expects integers, so any floats need to be rounded and converted

6 years ago+ 0 comments

Getting the data from .json file is taking way too much time, are there any modules that reads list of json objects in python?

10 months ago+ 0 comments

Here's my solution. Not that clean but gets the job done:

# Enter your code here. Read input from STDIN. Print output to STDOUT
import json
import os
import sys
import numpy as np
from sklearn.linear_model import LinearRegression

def read_input():
    X_test = []
    for line in sys.stdin.readlines()[1:]:
        data = json.loads(line.rstrip("\n"))
        del data["serial"]
        X_test.append(list(data.values()))
    return np.array(X_test)

def read_training_data():
    X_train = []
    y_train = []
    with open("training.json") as f:
        np_string = np.array(f.read().split("\n"))[1:-1]
        for json_obj in np_string:
            data = json.loads(json_obj)
            y_train.append(data["Mathematics"])
            del data["Mathematics"]
            del data["serial"]
            X_train.append(list(data.values()))
        f.close()
    return np.array(X_train), np.array(y_train)

def train():
    X_train, y_train = read_training_data()
    X_test = read_input()
    lin_reg = LinearRegression()
    lin_reg.fit(X_train, y_train)
    y_test = lin_reg.predict(X_test).astype(np.uint8)
    return y_test

def show(y):
    y_string = [str(y[k]) for k in range(len(y))]
    print("\n".join(y_string))

if __name__ == "__main__":
    show(train())

1 year ago+ 0 comments

My solution in Python deploys LDA to predict Math score. I was hoping to code in R but reading JSON files in R I get timed out.

import pandas as pd 
import json
import numpy as np
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA

num_lines = int(input())
inputs = [json.loads(input()) for _ in range(num_lines)]
test_df = pd.DataFrame(inputs).fillna(0)
with open('training.json') as f:
    data = [json.loads(line) for line in f]
    data.remove(data[0])
    train_df = pd.DataFrame(data).fillna(0)

test_df = test_df.drop(columns=['serial'])
train_df = train_df.drop(columns=['serial'])
missing_cols = list(train_df.columns.difference(test_df.columns))

if len(missing_cols) > 1:
    zeros = [0 for i in range(len(test_df))]
    for c in missing_cols:
        train_df[c] = zeros

X_train = train_df[['Physics','Chemistry','PhysicalEducation','English','Biology','Accountancy','BusinessStudies','Economics','ComputerScience']]
Y_train = train_df['Mathematics']

model = LDA()
X_train = model.fit(X_train.to_numpy(), Y_train.values.ravel())
X_test = test_df.to_numpy()

out = model.predict(X_test)
for i in out:
    print(i)

4 weeks ago+ 0 comments

import json
import os
import sys
import numpy as np
from sklearn.linear_model import LinearRegression

def loadTestingData():
    x = []
    n = int(input())
    
    for i in range(n):
        item = json.loads(input())
        del item['serial']
        x.append(list(item.values()))
    return np.array(x)

def loadTrainingData():
    x = []
    y = []
    with open('training.json') as f:
        lines = f.readlines()[0:5]
        lines.pop(0)
        for line in lines:
            item = json.loads(line)
            y.append([item['Mathematics']])
            
            del item['Mathematics']
            del item['serial']
            
            x.append(list(item.values()))
    return np.array(x), np.array(y)
    
def main():
    xTrain, yTrain = loadTrainingData()
    xTest = loadTestingData()
    
    model = LinearRegression().fit(xTrain, yTrain)
    result = model.predict(xTest).flatten()
    
    for item in result:
        print(round(item))
    
if __name__ == "__main__":
    main()

Load more conversations