import matplotlib.pyplot as plt
import numpy as np
from scipy import integrate
import pandas as pd
# from tqdm import tqdm #Import all needed modules

columns = ["Material", "Density", "Radius", "Mass", "Temperature", "Pressure", "Height", "Time"]
columnsNoMaterial = ["Density", "Radius", "Mass", "Temperature", "Pressure", "Height", "Time"]
units = ["", "kg/m^3", "m", "kg", "K", "Pa", "m", "s"]
materials = ["magnesium", "polycarbonate", "silica", "zinc_oxide", "silicon_carbide", "titanium", "iron"]
radii = [0.005, 0.01, 0.015, 0.02, 0.025]

def getData(file):
    columns = ["Material", "Density", "Radius", "Mass", "Temperature", "Pressure", "Height", "Time"]
    data = pd.read_csv(file, sep=',', names=columns, skiprows=9, on_bad_lines='skip')

    data["Density"] = pd.to_numeric(data["Density"], errors='coerce')
    data["Temperature"] = pd.to_numeric(data["Temperature"], errors='coerce')
    data["Time"] = pd.to_numeric(data["Time"], errors='coerce')
    
    for column in columns:
        if column == "Material":
            for i in data.index:
                if data[column][i] not in materials:
                    data.drop(i, inplace=True)
        else:
            for i in data.index:
                    if data[column][i] < 0:
                        data.loc[i, column] = -data.loc[i, column]

    data.dropna(inplace=True)
    return data

def columnStats(column, units):
    min = df[column].min()
    max = df[column].max()
    mean = df[column].mean()
    stdDev = df[column].std()

    print(f'Statistics for {column}')
    print(f'Minimum: {min}{units}')
    print(f'Maximum: {max}{units}')
    print(f'Mean: {mean}{units}')
    print(f'Standard Deviation: {stdDev}{units}')
    print()

df = getData('exercise3data.csv')

# for i in range(len(columns)):
#     if columns[i] == "Material":
#         continue
#     else:
#         columnStats(columns[i], units[i])

# for material in materials:
#     materialDf = df[df["Material"] == material]
#     for radius in radii:
#         radiusDf = materialDf[materialDf["Radius"] == radius]
#         print(radiusDf)
#         plt.scatter(radiusDf["Height"], radiusDf["Time"], label=f'Radius {radius}m')

#     plt.xlabel("Drop Height/m")
#     plt.ylabel("Fall Time/s")
#     plt.title(f'Material: {material}')
#     plt.legend()
#     plt.show()

dfNoMaterial = df.drop("Material", axis=1)
corrMatrix = dfNoMaterial.corr(method='pearson')
print(corrMatrix)

fig, ax = plt.subplots()
im = ax.imshow(corrMatrix, cmap="gnuplot", vmin=-1, vmax=1)

ax.set_xticks(range(len(columnsNoMaterial)), labels=columnsNoMaterial)
ax.set_yticks(range(len(columnsNoMaterial)), labels=columnsNoMaterial)

for i in range(len(columnsNoMaterial)):
    for j in range(len(columnsNoMaterial)):
        text = ax.text(j, i, round(corrMatrix[columnsNoMaterial[i]][columnsNoMaterial[j]], 2),
                       ha="center", va="center", color="w")

fig.colorbar(im)
fig.tight_layout()
plt.show()